Decision makers may suffer from uncertainty induced by limited data. This may be mitigated by accounting for epistemic uncertainty, which is however challenging to estimate efficiently for large neural networks. To this extent we investigate Delta Variances, a family of algorithms for epistemic uncertainty quantification, that is computationally efficient and convenient to implement. It can be applied to neural networks and more general functions composed of neural networks. As an example we consider a weather simulator with a neural-network-based step function inside - here Delta Variances empirically obtain competitive results at the cost of a single gradient computation. The approach is convenient as it requires no changes to the neural network architecture or training procedure. We discuss multiple ways to derive Delta Variances theoretically noting that special cases recover popular techniques and present a unified perspective on multiple related methods. Finally we observe that this general perspective gives rise to a natural extension and empirically show its benefit.

Gradient-based bilevel optimisation is a powerful technique with applications in hyperparameter optimisation, task adaptation, algorithm discovery, meta-learning more broadly, and beyond. It often requires differentiating through the gradient-based optimisation process itself, leading to "gradient-of-a-gradient" calculations with computationally expensive second-order and mixed derivatives. While modern automatic differentiation libraries provide a convenient way to write programs for calculating these derivatives, they oftentimes cannot fully exploit the specific structure of these problems out-of-the-box, leading to suboptimal performance. In this paper, we analyse such cases and propose Mixed-Flow Meta-Gradients, or MixFlow-MG -- a practical algorithm that uses mixed-mode differentiation to construct more efficient and scalable computational graphs yielding over 10x memory and up to 25\% wall-clock time improvements over standard implementations in modern meta-learning setups.

We introduce Wasserstein Policy Optimization (WPO), an actor-critic algorithm for reinforcement learning in continuous action spaces. WPO can be derived as an approximation to Wasserstein gradient flow over the space of all policies projected into a finite-dimensional parameter space (e.g., the weights of a neural network), leading to a simple and completely general closed-form update. The resulting algorithm combines many properties of deterministic and classic policy gradient methods. Like deterministic policy gradients, it exploits knowledge of the *gradient* of the action-value function with respect to the action. Like classic policy gradients, it can be applied to stochastic policies with arbitrary distributions over actions -- without using the reparameterization trick. We show results on the DeepMind Control Suite and a magnetic confinement fusion task which compare favorably with state-of-the-art continuous control methods.

The quality of foundation models depends heavily on their training data. Consequently, great efforts have been put into dataset curation. Yet most approaches rely on manual tuning of coarse-grained mixtures of large buckets of data, or filtering by hand-crafted heuristics. An approach that is ultimately more scalable (let alone more satisfying) is to \emph{learn} which data is actually valuable for training. This type of meta-learning could allow more sophisticated, fine-grained, and effective curation. Our proposed \emph{DataRater} is an instance of this idea. It estimates the value of training on any particular data point. This is done by meta-learning using `meta-gradients', with the objective of improving training efficiency on held out data. In extensive experiments across a range of model scales and datasets, we find that using our DataRater to filter data is highly effective, resulting in significantly improved compute efficiency.

Normalization layers have recently experienced a renaissance in the deep reinforcement learning and continual learning literature, with several works highlighting diverse benefits such as improving loss landscape conditioning and combatting overestimation bias. However, normalization brings with it a subtle but important side effect: an equivalence between growth in the norm of the network parameters and decay in the effective learning rate. This becomes problematic in continual learning settings, where the resulting learning rate schedule may decay to near zero too quickly relative to the timescale of the learning problem. We propose to make the learning rate schedule explicit with a simple re-parameterization which we call Normalize-and-Project (NaP), which couples the insertion of normalization layers with weight projection, ensuring that the effective learning rate remains constant throughout training. This technique reveals itself as a powerful analytical tool to better understand learning rate schedules in deep reinforcement learning, and as a means of improving robustness to nonstationarity in synthetic plasticity loss benchmarks along with both the single-task and sequential variants of the Arcade Learning Environment. We also show that our approach can be easily applied to popular architectures such as ResNets and transformers while recovering and in some cases even slightly improving the performance of the base model in common stationary benchmarks.

How to efficiently explore in reinforcement learning is an open problem. Many exploration algorithms employ the epistemic uncertainty of their own value predictions -- for instance to compute an exploration bonus or upper confidence bound. Unfortunately the required uncertainty is difficult to estimate in general with function approximation. We propose epistemic value estimation (EVE): a recipe that is compatible with sequential decision making and with neural network function approximators. It equips agents with a tractable posterior over all their parameters from which epistemic value uncertainty can be computed efficiently. We use the recipe to derive an epistemic Q-Learning agent and observe competitive performance on a series of benchmarks. Experiments confirm that the EVE recipe facilitates efficient exploration in hard exploration tasks.

In a standard view of the reinforcement learning problem, an agent’s goal is to efficiently identify a policy that maximizes long-term reward. However, this perspective is based on a restricted view of learning as finding a solution, rather than treating learning as endless adaptation. In contrast, continual reinforcement learning refers to the setting in which the best agents never stop learning. Despite the importance of continual reinforcement learning, the community lacks a simple definition of the problem that highlights its commitments and makes its primary concepts precise and clear. To this end, this paper is dedicated to carefully defining the continual reinforcement learning problem. We formalize the notion of agents that “never stop learning” through a new mathematical language for analyzing and cataloging agents. Using this new language, we define a continual learning agent as one that can be understood as carrying out an implicit search process indefinitely, and continual reinforcement learning as the setting in which the best agents are all continual learning agents. We provide two motivating examples, illustrating that traditional views of multi-task reinforcement learning and continual supervised learning are special cases of our definition. Collectively, these definitions and perspectives formalize many intuitive concepts at the heart of learning, and open new research pathways surrounding continual learning agents.

We study the connection between gradient-based meta-learning and convex optimisation. We observe that gradient descent with momentum is a special case of meta-gradients, and building on recent results in optimisation, we prove convergence rates for meta learning in the single task setting. While a meta-learned update rule can yield faster convergence up to constant factor, it is not sufficient for acceleration. Instead, some form of optimism is required. We show that optimism in meta-learning can be captured through the recently proposed Bootstrapped Meta-Gradient (Flennerhag et. al., 2022) method, providing deeper insight into its underlying mechanics.

Off-policy sampling and experience replay are key for improving sample efficiency and scaling model-free temporal difference learning methods. When combined with function approximation, such as neural networks, this combination is known as the deadly triad and is potentially unstable. Recently, it has been shown that stability and good performance at scale can be achieved by combining emphatic weightings and multi-step updates. This approach, however, is generally limited to sampling complete trajectories in order, to compute the required emphatic weighting. In this paper we investigate how to combine emphatic weightings with non-sequential, off-line data sampled from a replay buffer. We develop a multi-step emphatic weighting that can be combined with replay, and a time-reversed n-step TD learning algorithm to learn the required emphatic weighting. We show that these state weightings reduce variance compared with prior approaches, while providing convergence guarantees. We tested the approach at scale on Atari 2600 video games, and observed that the new X-ETD(n) agent improved over baseline agents, highlighting both the scalability and broad applicability of our approach.

Meta reinforcement learning (RL) attempts to discover new RL algorithms automatically from environment interaction. In so-called black-box approaches, the policy and the learning algorithm are jointly represented by a single neural network. These methods are very flexible, but they tend to underperform compared to human-engineered RL algorithms in terms of generalisation to new, unseen environments. In this paper, we explore the role of symmetries in meta-generalisation. We show that a recent successful meta RL approach that meta-learns an objective for backpropagation-based learning exhibits certain symmetries (specifically the reuse of the learning rule, and invariance to input and output permutations) that are not present in typical black-box meta RL systems. We hypothesise that these symmetries can play an important role in meta-generalisation. Building off recent work in black-box supervised meta learning, we develop a black-box meta RL system that exhibits these same symmetries. We show through careful experimentation that incorporating these symmetries can lead to algorithms with a greater ability to generalise to unseen action & observation spaces, tasks, and environments.

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or because the experience was generated out of its own control. However, off-policy learning is non-trivial, and standard reinforcement-learning algorithms can be unstable and divergent. In this paper we discuss a novel family of off-policy prediction algorithms which are convergent by construction. The idea is to first learn on-policy about the data-generating behaviour, and then bootstrap an off-policy value estimate on this on-policy estimate, thereby constructing a value estimate that is partially off-policy. This process can be repeated to build a chain of value functions, each time bootstrapping a new estimate on the previous estimate in the chain. Each step in the chain is stable and hence the complete algorithm is guaranteed to be stable. Under mild conditions this comes arbitrarily close to the off-policy TD solution when we increase the length of the chain. Hence it can compute the solution even in cases where off-policy TD diverges. We prove that the proposed scheme is convergent and corresponds to an iterative decomposition of the inverse key matrix. Furthermore it can be interpreted as estimating a novel objective -- that we call a `k-step expedition' -- of following the target policy for finitely many steps before continuing indefinitely with the behaviour policy. Empirically we evaluate the idea on challenging MDPs such as Baird's counter example and observe favourable results.

The question of how to determine which states and actions are responsible for a certain outcome is known as the credit assignment problem and remains a central research question in reinforcement learning and artificial intelligence. Eligibility traces enable efficient credit assignment to the recent sequence of states and actions experienced by the agent, but not to counterfactual sequences that could also have led to the current state. In this work, we introduce expected eligibility traces. Expected traces allow, with a single update, to update states and actions that could have preceded the current state, even if they did not do so on this occasion. We discuss when expected traces provide benefits over classic (instantaneous) traces in temporal-difference learning, and show that some- times substantial improvements can be attained. We provide a way to smoothly interpolate between instantaneous and expected traces by a mechanism similar to bootstrapping, which ensures that the resulting algorithm is a strict generalisation of TD(λ). Finally, we discuss possible extensions and connections to related ideas, such as successor features.

We propose a novel policy update that combines regularized policy optimization with model learning as an auxiliary loss. The update (henceforth Muesli) matches MuZero’s state-of-the-art performance on Atari. Notably, Muesli does so without using deep search: it acts directly with a policy network and has computation speed comparable to model-free baselines. The Atari results are complemented by extensive ablations, and by additional results on continuous control and 9x9 Go.

Off-policy learning allows us to learn about possible policies of behavior from experience generated by a different behavior policy. Temporal difference (TD) learning algorithms can become unstable when combined with function approximation and off-policy sampling—this is known as the “deadly triad”. Emphatic temporal difference (ETD($\lambda$)) algorithm ensures convergence in the linear case by appropriately weighting the TD($\lambda$) updates. In this paper, we extend the use of emphatic methods to deep reinforcement learning agents. We show that naively adapting ETD($\lambda$) to popular deep reinforcement learning algorithms, which use forward view multi-step returns, results in poor performance. We then derive new emphatic algorithms for use in the context of such algorithms, and we demonstrate that they provide noticeable benefits in small problems designed to highlight the instability of TD methods. Finally, we observed improved performance when applying these algorithms at scale on classic Atari games from the Arcade Learning Environment.

Learned models of the environment provide reinforcement learning (RL) agents with flexible ways of making predictions about the environment.Models enable planning, i.e. using more computation to improve value functions or policies, without requiring additional environment interactions.In this work, we investigate a way of augmenting model-based RL, by additionally encouraging a learned model and value function to be jointly \emph{self-consistent}.This lies in contrast to classic planning methods like Dyna, which only update the value function to be consistent with the model.We propose a number of possible self-consistency updates, study them empirically in both the tabular and function approximation settings, and find that with appropriate choices self-consistency can be useful both for policy evaluation and control.

Temporal abstractions in the form of options have been shown to help reinforcement learning (RL) agents learn faster. However, despite prior work on this topic, the problem of discovering options through interaction with an environment remains a challenge. In this paper, we introduce a novel meta-gradient approach for discovering useful options in multi-task RL environments. Our approach is based on a manager-worker decomposition of the RL agent, in which a manager maximises rewards from the environment by learning a task-dependent policy over both a set of task-independent discovered-options and primitive actions. The option-reward and termination functions that define a subgoal for each option are parameterised as neural networks and trained via meta-gradients to maximise their usefulness. Empirical analysis on gridworld and DeepMind Lab tasks show that: (1) our approach can discover meaningful and diverse temporally-extended options in multi-task RL domains, (2) the discovered options are frequently used by the agent while learning to solve the training tasks, and (3) that the discovered options help a randomly initialised manager learn faster in completely new tasks.

The principal contribution of this paper is a conceptual framework for off-policy reinforcement learning, based on conditional expectations of importance sampling ratios. This framework yields new perspectives and understanding of existing off-policy algorithms, and reveals a broad space of unexplored algorithms. We theoretically analyse this space, and concretely investigate several algorithms that arise from this framework.

The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition that the reward function itself can be a good locus of learned knowledge. To investigate this, we propose a scalable meta-gradient framework for learning useful intrinsic reward functions across multiple lifetimes of experience. Through several proof-of-concept experiments, we show that it is feasible to learn and capture knowledge about long-term exploration and exploitation into a reward function. Furthermore, we show that unlike policy transfer methods that capture “how” the agent should behave, the learned reward functions can generalise to other kinds of agents and to changes in the dynamics of the environment by capturing “what” the agent should strive to do.

We address the problem of credit assignment in reinforcement learning and explore fundamental questions regarding the way in which an agent can best use additional computation to propagate new information, by planning with internal models of the world to improve its predictions. Particularly, we work to understand the gains and peculiarities of planning employed as forethought via forward models or as hindsight operating with backward models. We establish the relative merits, limitations and complementary properties of both planning mechanisms in carefully constructed scenarios. Further, we investigate the best use of models in planning, primarily focusing on the selection of states in which predictions should be (re)-evaluated. Lastly, we discuss the issue of model estimation and highlight a spectrum of methods that stretch from environment dynamics predictors to planner-aware models.

Reinforcement learning (RL) algorithms update an agent’s parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient algorithms, or algorithms that are better adapted to specific environments. Although there have been prior attempts at addressing this significant scientific challenge, it remains an open question whether it is feasible to discover alternatives to fundamental concepts of RL such as value functions and temporal-difference learning. This paper introduces a new meta-learning approach that discovers an entire update rule which includes both what to predict' (e.g. value functions) andhow to learn from it' (e.g. bootstrapping) by interacting with a set of environments. The output of this method is an RL algorithm that we call Learned Policy Gradient (LPG). Empirical results show that our method discovers its own alternative to the concept of value functions. Furthermore it discovers a bootstrapping mechanism to maintain and use its predictions. Surprisingly, when trained solely on toy environments, LPG generalises effectively to complex Atari games and achieves non-trivial performance. This shows the potential to discover general RL algorithms from data.

Deep reinforcement learning includes a broad family of algorithms that parameterise an internal representation, such as a value function or policy, by a deep neural network. Each algorithm optimises its parameters with respect to an objective, such as Q-learning or policy gradient, that defines its semantics. In this work, we propose an algorithm based on meta-gradient descent that discovers its own objective, flexibly parameterised by a deep neural network, solely from interactive experience with its environment. Over time, this allows the agent to learn how to learn increasingly effectively. Furthermore, because the objective is discovered online, it can adapt to changes over time. We demonstrate that the algorithm discovers how to address several important issues in RL, such as bootstrapping, non-stationarity, and off-policy learning. On the Atari Learning Environment, the meta-gradient algorithm adapts over time to learn with greater efficiency, eventually outperforming the median score of a strong actor-critic baseline.

Reinforcement learning algorithms are highly sensitive to the choice of hyperparameters, typically requiring significant manual effort to identify hyperparameters that perform well on a new domain. In this paper, we take a step towards addressing this issue by using metagradients to automatically adapt hyperparameters online by meta-gradient descent (Xu et al., 2018). We apply our algorithm, Self-Tuning Actor-Critic (STAC), to self-tune all the differentiable hyperparameters of an actor-critic loss function, to discover auxiliary tasks, and to improve off-policy learning using a novel leaky V-trace operator. STAC is simple to use, sample efficient and does not require a significant increase in compute. Ablative studies show that the overall performance of STAC improved as we adapt more hyperparameters. When applied to the Arcade Learning Environment (Bellemare et al. 2012), STAC improved the median human normalized score in 200M steps from 243% to 364%. When applied to the DM Control suite (Tassa et al., 2018), STAC improved the mean score in 30M steps from 217 to 389 when learning with features, from 108 to 202 when learning from pixels, and from 195 to 295 in the Real-World Reinforcement Learning Challenge (Dulac-Arnold et al., 2020).

The reinforcement learning (RL) community has made great strides in designing algorithms capable of exceeding human performance on specific tasks. These algorithms are mostly trained one task at the time, each new task requiring to train a brand new agent instance. This means the learning algorithm is general, but each solution is not; each agent can only solve the one task it was trained on. In this work, we study the problem of learning to master not one but multiple sequentialdecision tasks at once. A general issue in multi-task learning is that a balance must be found between the needs of multiple tasks competing for the limited resources of a single learning system. Many learning algorithms can get distracted by certain tasks in the set of tasks to solve. Such tasks appear more salient to the learning process, for instance because of the density or magnitude of the in-task rewards. This causes the algorithm to focus on those salient tasks at the expense of generality. We propose to automatically adapt the contribution of each task to the agent’s updates, so that all tasks have a similar impact on the learning dynamics. This resulted in state of the art performance on learning to play all games in a set of 57 diverse Atari games. Excitingly, our method learned a single trained policy - with a single set of weights - that exceeds median human performance. To our knowledge, this was the first time a single agent surpassed human-level performance on this multi-task domain. The same approach also demonstrated state of the art performance on a set of 30 tasks in the 3D reinforcement learning platform DeepMind Lab.

We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit to past decisions based on the likelihood of them having led to the observed outcome. This approach uses new information in hindsight, rather than employing foresight. Somewhat surprisingly, we show that value functions can be rewritten through this lens, yielding a new family of algorithms. We study the properties of these algorithms, and empirically show that they successfully address important credit assignment challenges, through a set of illustrative tasks.

We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, including the ability to plan: to use more computation without additional data to improve predictions and behaviour. We discuss when to expect benefits from either approach, and interpret prior work in this context. We hypothesise that, under suitable conditions, replay-based algorithms should be competitive to or better than model-based algorithms if the model is used only to generate fictional transitions from observed states for an update rule that is otherwise model-free. We validated this hypothesis on Atari 2600 video games. The replay-based algorithm attained state-of-the-art data efficiency, improving over prior results with parametric models. Additionally, we discuss different ways to use models. We show that it can be better to plan backward than to plan forward when using models to perform credit assignment (e.g., to directly learn a value or policy), even though the latter seems more common. Finally, we argue and demonstrate that it can be beneficial to plan forward for immediate behaviour, rather than for credit assignment.

Arguably, intelligent agents ought to be able to discover their own questions so that in learning answers for them they learn unanticipated useful knowledge and skills; this departs from the focus in much of machine learning on agents learning answers to externally defined questions. We present a novel method for a reinforcement learning (RL) agent to discover questions formulated as general value functions or GVFs, a fairly rich form of knowledge representation. Specifically, our method uses non-myopic meta-gradients to learn GVF-questions such that learning answers to them, as an auxiliary task, induces useful representations for the main task faced by the RL agent. We demonstrate that auxiliary tasks based on the discovered GVFs are sufficient, on their own, to build representations that support main task learning, and that they do so better than popular hand-designed auxiliary tasks from the literature. Furthermore, we show, in the context of Atari2600 videogames, how such auxiliary tasks, meta-learned alongside the main task, can improve the data efficiency of an actor-critic agent.

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN algorithm and empirically studies their combination. Our experiments show that the combination provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and final performance. We also provide results from a detailed ablation study that shows the contribution of each component to overall performance.

Learning to coordinate between multiple agents is an important problem in many reinforcement learning problems. Key to learning to coordinate is exploiting loose couplings, i.e., conditional independences between agents. In this paper we study learning in repeated fully cooperative games, multi-agent multi-armed bandits (MAMABs), in which the expected rewards can be expressed as a coordination graph. We propose multi-agent upper confidence exploration (MAUCE), a new algorithm for MAMABs that exploits loose couplings, which enables us to prove a regret bound that is logarithmic in the number of arm pulls and only linear in the number of agents. We empirically compare MAUCE to sparse cooperative Q-learning, and a state-of-the-art combinatorial bandit approach, and show that it performs much better on a variety of settings, including learning control policies for wind farms.

The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of reinforcement learning algorithms estimate and/or optimise a proxy for the value function. This proxy is typically based on a sampled and bootstrapped approximation to the true value function, known as a return. The particular choice of return is one of the chief components determining the nature of the algorithm: the rate at which future rewards are discounted; when and how values should be bootstrapped; or even the nature of the rewards themselves. It is well-known that these decisions are crucial to the overall success of RL algorithms. We discuss a gradient-based meta-learning algorithm that is able to adapt the nature of the return, online, whilst interacting and learning from the environment. When applied to 57 games on the Atari 2600 environment over 200 million frames, our algorithm achieved a new state-of-the-art performance.

One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning. In this document we introduce the predictron architecture. The predictron consists of a fully abstract model, represented by a Markov reward process, that can be rolled forward multiple “imagined” planning steps. Each forward pass of the predictron accumulates internal rewards and values over multiple planning depths. The predictron is trained end-to-end so as to make these accumulated values accurately approximate the true value function. We applied the predictron to procedurally generated random mazes and a simulator for the game of pool. The predictron yielded significantly more accurate predictions than conventional deep neural network architectures.

Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes between tasks but the environment's dynamics remain the same. Our approach rests on two key ideas: "successor features", a value function representation that decouples the dynamics of the environment from the rewards, and "generalized policy improvement", a generalization of dynamic programming's policy improvement operation that considers a set of policies rather than a single one. Put together, the two ideas lead to an approach that integrates seamlessly within the reinforcement learning framework and allows the free exchange of information across tasks. The proposed method also provides performance guarantees for the transferred policy even before any learning has taken place. We derive two theorems that set our approach in firm theoretical ground and present experiments that show that it successfully promotes transfer in practice, significantly outperforming alternative methods in a sequence of navigation tasks and in the control of a simulated robotic arm.

Neural networks have a smooth initial inductive bias, such that small changes in input do not lead to large changes in output. However, in reinforcement learning domains with sparse rewards, value functions have non-smooth structure with a characteristic asymmetric discontinuity whenever rewards arrive. We propose a mechanism that learns an interpolation between a direct value estimate and a projected value estimate computed from the encountered reward and the previous estimate. This reduces the need to learn about discontinuities, and thus improves the value function approximation. Furthermore, as the interpolation is learned and state-dependent, our method can deal with heterogeneous observability. We demonstrate that this one change leads to significant improvements on multiple Atari games, when applied to the state-of-the-art A3C algorithm.

The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively. In particular, we first show that the recent DQN algorithm, which combines Q-learning with a deep neural network, suffers from substantial overestimations in some games in the Atari 2600 domain. We then show that the idea behind the Double Q-learning algorithm, which was introduced in a tabular setting, can be generalized to work with large-scale function approximation. We propose a specific adaptation to the DQN algorithm and show that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.

In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state value function and one for the state-dependent action advantage function. The main benefit of this factoring is to generalize learning across actions without imposing any change to the underlying reinforcement learning algorithm. Our results show that this architecture leads to better policy evaluation in the presence of many similar-valued actions. Moreover, the dueling architecture enables our RL agent to outperform the state-of-the-art on the Atari 2600 domain.

Most learning algorithms are not invariant to the scale of the signal that is being approximated. We propose to adaptively normalize the targets used in the learning updates. This is important in value-based reinforcement learning, where the magnitude of appropriate value approximations can change over time when we update the policy of behavior. Our main motivation is prior work on learning to play Atari games, where the rewards were clipped to a predetermined range. This clipping facilitates learning across many different games with a single learning algorithm, but a clipped reward function can result in qualitatively different behavior. Using adaptive normalization we can remove this domain-specific heuristic without diminishing overall performance.

Q-learning, the most popular of reinforcement learning algorithms, has always included an extension to eligibility traces to enable more rapid learning and improved asymptotic performance on non-Markov problems. The lambda parameter smoothly shifts on-policy algorithms such as TD(lambda) and Sarsa(lambda) from a pure bootstrapping form (lambda=0) to a pure Monte Carlo form (lambda=1). In off-policy algorithms, including Q(lambda), GQ(lambda), and off-policy LSTD(lambda), the lambda parameter is intended to play the same role, but does not; on every exploratory action these algorithms bootstrap regardless of the value of lambda, and as a result they fail to approximate Monte Carlo learning when lambda=1. It may seem that this is inevitable for any online off-policy algorithm; if updates are made on each step on which the target policy is followed, then how could just the right updates be ‘un-made’ upon deviation from the target policy? In this paper, we introduce a new version of Q(lambda) that does exactly that, without significantly increased algorithmic complexity. En route to our new Q(lambda), we introduce a new derivation technique based on the forward-view/backward-view analysis familiar from TD(lambda) but extended to apply at every time step rather than only at the end of episodes. We apply this technique to derive first a new off-policy version of TD(lambda), called PTD(lambda), and then our new Q(lambda), called PQ(lambda).

We describe a new framework for applying reinforcement learning (RL) algorithms to solve classification tasks by letting an agent act on the inputs and learn value functions. This paper describes how classification problems can be modeled using classification Markov decision processes and introduces the Max-Min ACLA algorithm, an extension of the novel RL algorithm called actor-critic learning automaton (ACLA). Experiments are performed using 8 datasets from the UCI repository, where our RL method is combined with multi-layer perceptrons that serve as function approximators. The RL method is compared to conventional multi-layer perceptrons and support vector machines and the results show that our method slightly outperforms the multi-layer perceptron and performs equally well as the support vector machine. Finally, many possible extensions are described to our basic method, so that much future research can be done to make the proposed method even better.

In some stochastic environments the well-known reinforcement learning algorithm Q-learning performs very poorly. This poor performance is caused by large overestimations of action values. These overestimations result from a positive bias that is introduced because Q-learning uses the maximum action value as an approximation for the maximum expected action value. We introduce an alternative way to approximate the maximum expected value for any set of random variables. The obtained double estimator method is shown to sometimes underestimate rather than overestimate the maximum expected value. We apply the double estimator to Q-learning to construct Double Q-learning, a new off-policy reinforcement learning algorithm. We show the new algorithm converges to the optimal policy and that it performs well in some settings in which Q-learning performs poorly due to its overestimation.

This paper presents a theoretical and empirical analysis of Expected Sarsa, a variation on Sarsa, the classic on-policy temporal-difference method for model-free reinforcement learning. Expected Sarsa exploits knowledge about stochasticity in the behavior policy to perform updates with lower variance. Doing so allows for higher learning rates and thus faster learning. In deterministic environments, Expected Sarsas updates have zero variance, enabling a learning rate of 1. We prove that Expected Sarsa converges under the same conditions as Sarsa and formulate specific hypotheses about when Expected Sarsa will outperform Sarsa and Q-learning. Experiments in multiple domains confirm these hypotheses and demonstrate that Expected Sarsa has significant advantages over these more commonly used methods.

This paper describes several new online model-free reinforcement learning (RL) algorithms. We designed three new reinforcement algorithms, namely: QV2, QVMAX, and QVMAX2, that are all based on the QV-learning algorithm, but in contrary to QV-learning, QVMAX and QVMAX2 are off-policy RL algorithms and QV2 is a new on-policy RL algorithm. We experimentally compare these algorithms to a large number of different RL algorithms, namely: Q-learning, Sarsa, R-learning, Actor-Critic, QV-learning, and ACLA. We show experiments on five maze problems of varying complexity. Furthermore, we show experimental results on the cart pole balancing problem. The results show that for different problems, there can be large performance differences between the different algorithms, and that there is not a single RL algorithm that always performs best, although on average QV-learning scores highest.

Real-world control problems are often modeled as Markov decision processes (MDPs) with discrete action spaces to facilitate the use of the many reinforcement learning algorithms that exist to find solutions for such MDPs. For many of these problems an underlying continuous action space can be assumed. We investigate the performance of the Cacla algorithm, which uses a continuous actor, on two such MDPs: the mountain car and the cart pole. We show that Cacla has clear advantages over discrete algorithms such as Q-learning and Sarsa, even though its continuous actions get rounded to actions in the same finite action space that may contain only a small number of actions. In particular, we show that Cacla retains much better performance when the action space is changed by removing some actions after some time of learning.

This paper describes several ensemble methods that combine multiple different reinforcement learning (RL) algorithms in a single agent. The aim is to enhance learning speed and final performance by combining the chosen actions or action probabilities of different RL algorithms. We designed and implemented four different ensemble methods combining the following five different RL algorithms: Q-learning, Sarsa, actor-critic (AC), QV-learning, and AC learning automaton. The intuitively designed ensemble methods, namely, majority voting (MV), rank voting, Boltzmann multiplication (BM), and Boltzmann addition, combine the policies derived from the value functions of the different RL algorithms, in contrast to previous work where ensemble methods have been used in RL for representing and learning a single value function. We show experiments on five maze problems of varying complexity; the first problem is simple, but the other four maze tasks are of a dynamic or partially observable nature. The results indicate that the BM and MV ensembles significantly outperform the single RL algorithms.