Large language models (LLMs) have shown significant potential for robotics applications, particularly task planning, by harnessing their language comprehension and text generation capabilities. However, in applications such as household robotics, a critical gap remains in the personalization of these models to household preferences. For example, an LLM planner may find it challenging to perform tasks that require personalization, such as deciding where to place mugs in a kitchen based on specific household preferences. We introduce LLM-Personalize, a novel framework designed to personalize LLM planners for household robotics. LLM-Personalize uses an LLM planner to perform iterative planning in multi-room, partially-observable household environments, utilizing a scene graph built dynamically from local observations. To personalize the LLM planner towards user preferences, our optimization pipeline integrates imitation learning and reinforced Self-Training. We evaluate LLM-Personalize on Housekeep, a challenging simulated real-world 3D benchmark for household rearrangements, demonstrating a more than 30 percent increase in success rate over existing LLM planners, showcasing significantly improved alignment with human preferences.

While agentic AI has advanced in automating individual tasks, managing complex multi-agent workflows remains a challenging problem. This paper presents a research vision for autonomous agentic systems that orchestrate collaboration within dynamic human-AI teams. We propose the Autonomous Manager Agent as a core challenge: an agent that decomposes complex goals into task graphs, allocates tasks to human and AI workers, monitors progress, adapts to changing conditions, and maintains transparent stakeholder communication. We formalize workflow management as a Partially Observable Stochastic Game and identify four foundational challenges: (1) compositional reasoning for hierarchical decomposition, (2) multi-objective optimization under shifting preferences, (3) coordination and planning in ad hoc teams, and (4) governance and compliance by design. To advance this agenda, we release MA-Gym, an open-source simulation and evaluation framework for multi-agent workflow orchestration. Evaluating GPT-5-based Manager Agents across 20 workflows, we find they struggle to jointly optimize for goal completion, constraint adherence, and workflow runtime–underscoring workflow management as a difficult open problem. We conclude with organizational and ethical implications of autonomous management systems.

Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further complexity to this challenge, as it is often unclear whether the same information will be relevant to both the actor and the critic. To this end, we here explore the principles that underlie effective representations for the actor and for the critic in on-policy algorithms. We focus our study on understanding whether the actor and critic will benefit from separate, rather than shared, representations. Our primary finding is that when separated, the representations for the actor and critic systematically specialise in extracting different types of information from the environment---the actor's representation tends to focus on action-relevant information, while the critic's representation specialises in encoding value and dynamics information. We conduct a rigourous empirical study to understand how different representation learning approaches affect the actor and critic's specialisations and their downstream performance, in terms of sample efficiency and generation capabilities. Finally, we discover that a separated critic plays an important role in exploration and data collection during training. Our code, trained models and data are accessible at https://github.com/francelico/deac-rep.

Reinforcement learning (RL) has shown remarkable success in training agents to achieve high-performing policies, particularly in domains like Game AI where simulation environments enable efficient interactions. However, despite their success in maximizing these returns, such online-trained policies often fail to align with human preferences concerning actions, styles, and values. The challenge lies in efficiently adapting these online-trained policies to align with human preferences, given the scarcity and high cost of collecting human behavior data. In this work, we formalize the problem as *online-to-offline* RL and propose ALIGNment of Game AI to Preferences (ALIGN-GAP), an innovative approach for the alignment of well-trained game agents to human preferences. Our method features a carefully designed reward model that encodes human preferences from limited offline data and incorporates curriculum-based preference learning to align RL agents with targeted human preferences. Experiments across diverse environments and preference types demonstrate the performance of ALIGN-GAP, achieving effective alignment with human preferences.

Adaptive cooperation in multi-agent reinforcement learning (MARL) requires policies to express homogeneous, specialised, or mixed behaviours, yet achieving this adaptivity remains a critical challenge. While parameter sharing (PS) is standard for efficient learning, it notoriously suppresses the behavioural diversity required for specialisation. This failure is largely due to cross-agent gradient interference, a problem we find is surprisingly exacerbated by the common practice of *coupling agent IDs with observations*. Existing remedies typically add complexity through altered objectives, manual preset diversity levels, or sequential updates -- raising a fundamental question: *can shared policies adapt without these intricacies?* We propose a solution built on a key insight: an agent-conditioned hypernetwork can generate agent-specific parameters and *decouple* observation- and agent-conditioned gradients, directly countering the interference from coupling agent IDs with observations. Our resulting method, **HyperMARL**, avoids the complexities of prior work and empirically reduces policy gradient variance. Across diverse MARL benchmarks (22 scenarios, up to 30 agents), HyperMARL achieves performance competitive with six key baselines while preserving behavioural diversity comparable to non-parameter sharing methods, establishing it as a versatile and principled approach for adaptive MARL. The code is publicly available at https://github.com/KaleabTessera/HyperMARL.

Publisher Copyright: © 2024 The Authors

Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a novel approach to representing the current task using reward machines (RMs), state machine abstractions that induce subtasks based on the current task’s rewards and dynamics. Our method provides agents with symbolic representations of optimal transitions from their current abstract state and rewards them for achieving these transitions. These representations are shared across tasks, allowing agents to exploit knowledge of previously encountered symbols and transitions, thus enhancing transfer. Empirical results show that our representations improve sample efficiency and few-shot transfer in a variety of domains.

Although much research has been done on proposing new models or loss functions to improve the generalisation of artificial neural networks (ANNs), less attention has been directed to the impact of the training data on generalisation. In this work, we start from approximating the interaction between samples, i.e. how learning one sample would modify the model's prediction on other samples. Through analysing the terms involved in weight updates in supervised learning, we find that labels influence the interaction between samples. Therefore, we propose the labelled pseudo Neural Tangent Kernel (lpNTK) which takes label information into consideration when measuring the interactions between samples. We first prove that lpNTK asymptotically converges to the empirical neural tangent kernel in terms of the Frobenius norm under certain assumptions. Secondly, we illustrate how lpNTK helps to understand learning phenomena identified in previous work, specifically the learning difficulty of samples and forgetting events during learning. Moreover, we also show that using lpNTK to identify and remove poisoning training samples does not hurt the generalisation performance of ANNs.

Autonomous agents trained using deep reinforcement learning (RL) often lack the ability to successfully generalise to new environments, even when these environments share characteristics with the ones they have encountered during training. In this work, we investigate how the sampling of individual environment instances, or levels, affects the zero-shot generalisation (ZSG) ability of RL agents. We discover that, for deep actor-critic architectures sharing their base layers, prioritising levels according to their value loss minimises the mutual information between the agent’s internal representation and the set of training levels in the generated training data. This provides a novel theoretical justification for the regularisation achieved by certain adaptive sampling strategies. We then turn our attention to unsupervised environment design (UED) methods, which assume control over level generation. We find that existing UED methods can significantly shift the training distribution, which translates to low ZSG performance. To prevent both overfitting and distributional shift, we introduce data-regularised environment design (DRED). DRED generates levels using a generative model trained to approximate the ground truth distribution of an initial set of level parameters. Through its grounding, DRED achieves significant improvements in ZSG over adaptive level sampling strategies and UED methods.

We consider a warehouse in which dozens of mobile robots and human pickers work together to collect and deliver items within the warehouse. The fundamental problem we tackle, called the order-picking problem, is how these worker agents must coordinate their movement and actions in the warehouse to maximise performance in this task. Established industry methods using heuristic approaches require large engineering efforts to optimise for innately variable warehouse configurations. In contrast, multi-agent reinforcement learning (MARL) can be flexibly applied to diverse warehouse configurations (e.g. size, layout, number/types of workers, item replenishment frequency), and different types of order-picking paradigms (e.g. Goods-to-Person and Person-to-Goods), as the agents can learn how to cooperate optimally through experience. We develop hierarchical MARL algorithms in which a manager agent assigns goals to worker agents, and the policies of the manager and workers are co-trained toward maximising a global objective (e.g. pick rate). Our hierarchical algorithms achieve significant gains in sample efficiency over baseline MARL algorithms and overall pick rates over multiple established industry heuristics in a diverse set of warehouse configurations and different order-picking paradigms.

Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with varying environmental features that require different optimal skills (i.e., different modes of behaviour). Using context encoders based on contrastive learning to enhance the generalisability of Meta-RL agents is now widely studied but faces challenges such as the requirement for a large sample size, also referred to as the $\log$-$K$ curse. To improve RL generalisation to different tasks, we first introduce Skill-aware Mutual Information (SaMI), an optimisation objective that aids in distinguishing context embeddings according to skills, thereby equipping RL agents with the ability to identify and execute different skills across tasks. We then propose Skill-aware Noise Contrastive Estimation (SaNCE), a $K$-sample estimator used to optimise the SaMI objective. We provide a framework for equipping an RL agent with SaNCE in practice and conduct experimental validation on modified MuJoCo and Panda-gym benchmarks. We empirically find that RL agents that learn by maximising SaMI achieve substantially improved zero-shot generalisation to unseen tasks. Additionally, the context encoder trained with SaNCE demonstrates greater robustness to a reduction in the number of available samples, thus possessing the potential to overcome the $\log$-$K$ curse.

Artificial Intelligence (AI) shows promising applications for the perception and planning tasks in autonomous driving (AD) due to its superior performance compared to conventional methods. However, highly complex AI systems exacerbate the existing challenge of safety assurance of AD. One way to mitigate this challenge is to utilize explainable AI (XAI) techniques. To this end, we present the first comprehensive systematic literature review of explainable methods for safe and trustworthy AD. We begin by analyzing the requirements for AI in the context of AD, focusing on three key aspects: data, model, and agency. We find that XAI is fundamental to meeting these requirements. Based on this, we explain the sources of explanations in AI and describe a taxonomy of XAI. We then identify five key contributions of XAI for safe and trustworthy AI in AD, which are interpretable design, interpretable surrogate models, interpretable monitoring, auxiliary explanations, and interpretable validation. Finally, we propose a conceptual modular framework called SafeX to integrate the reviewed methods, enabling explanation delivery to users while simultaneously ensuring the safety of AI models.

Reasoning with occluded traffic agents is a significant open challenge for planning for autonomous vehicles. Recent deep learning models have shown impressive results for predicting occluded agents based on the behaviour of nearby visible agents; however, as we show in experiments, these models are difficult to integrate into downstream planning. To this end, we propose Bi-Ievel Variational Occlusion Models (BiVO), a two-step generative model that first predicts likely locations of occluded agents, and then generates likely trajectories for the occluded agents. In contrast to existing methods, BiVO outputs a trajectory distribution which can then be sampled from and integrated into standard downstream planning. We evaluate the method in closed-loop replay simulation using the real-world nuScenes dataset. Our results suggest that BiVO can successfully learn to predict occluded agent trajectories, and these predictions lead to better subsequent motion plans in critical scenarios.

Goal recognition (GR) involves inferring the goals of other vehicles, such as a certain junction exit, which can enable more accurate prediction of their future behaviour. In autonomous driving, vehicles can encounter many different scenarios and the environment may be partially observable due to occlusions. We present a novel GR method named Goal Recognition with Interpretable Trees under Occlusion (OGRIT). OGRIT uses decision trees learned from vehicle trajectory data to infer the probabilities of a set of generated goals. We demonstrate that OGRIT can handle missing data due to occlusions and make inferences across multiple scenarios using the same learned decision trees, while being computationally fast, accurate, interpretable and verifiable. We also release the inDO, rounDO and OpenDDO datasets of occluded regions used to evaluate OGRIT.

Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading correlations in their latent representation, preventing the agent from generalising if the correlation changes within the environment or when deployed in the real world. Disentangled representations can improve robustness, but existing disentanglement techniques that minimise mutual information between features require independent features, thus they cannot disentangle correlated features. We propose an auxiliary task for RL algorithms that learns a disentangled representation of high-dimensional observations with correlated features by minimising the conditional mutual information between features in the representation. We demonstrate experimentally, using continuous control tasks, that our approach improves generalisation under correlation shifts, as well as improving the training performance of RL algorithms in the presence of correlated features.

Open ad hoc teamwork is the problem of training a single agent to efficiently collaborate with an unknown group of teammates whose composition may change over time. A variable team composition creates challenges for the agent, such as the requirement to adapt to new team dynamics and dealing with changing state vector sizes. These challenges are aggravated in real-world applications in which the controlled agent only has a partial view of the environment. In this work, we develop a class of solutions for open ad hoc teamwork under full and partial observability. We start by developing a solution for the fully observable case that leverages graph neural network architectures to obtain an optimal policy based on reinforcement learning. We then extend this solution to partially observable scenarios by proposing different methodologies that maintain belief estimates over the latent environment states and team composition. These belief estimates are combined with our solution for the fully observable case to compute an agent's optimal policy under partial observability in open ad hoc teamwork. Empirical results demonstrate that our solution can learn efficient policies in open ad hoc teamwork in fully and partially observable cases. Further analysis demonstrates that our methods' success is a result of effectively learning the effects of teammates' actions while also inferring the inherent state of the environment under partial observability.

Motion prediction of road users in traffic scenes is critical for autonomous driving systems that must take safe and robust decisions in complex dynamic environments. We present a novel motion prediction system for autonomous driving. Our system is based on the Bayesian inverse planning framework, which efficiently orchestrates map-based goal extraction, a classical control-based trajectory generator and a mixture of experts collection of light-weight neural networks specialised in motion profile prediction. In contrast to many alternative methods, this modularity helps isolate performance factors and better interpret results, without compromising performance. This system addresses multiple aspects of interest, namely multi-modality, motion profile uncertainty and trajectory physical feasibility. We report on several experiments with the popular highway dataset NGSIM, demonstrating state-of-the-art performance in terms of trajectory error. We also perform a detailed analysis of our system's components, along with experiments that stratify the data based on behaviours, such as change-lane versus follow-lane, to provide insights into the challenges in this domain. Finally, we present a qualitative analysis to show other benefits of our approach, such as the ability to interpret the outputs.

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle distinction between on-policy data and on-policy sampling in the context of the RL sub-problem of policy evaluation. We observe that on-policy sampling may fail to match the expected distribution of on-policy data after observing only a finite number of trajectories and this failure hinders data-efficient policy evaluation. Towards improved data-efficiency, we show how non-i.i.d., off-policy sampling can produce data that more closely matches the expected on-policy data distribution and consequently increases the accuracy of the Monte Carlo estimator for policy evaluation. We introduce a method called Robust On-Policy Sampling and demonstrate theoretically and empirically that it produces data that converges faster to the expected on-policy distribution compared to on-policy sampling. Empirically, we show that this faster convergence leads to lower mean squared error policy value estimates.

Recent road trials have shown that guaranteeing the safety of driving decisions is essential for the wider adoption of autonomous vehicle technology. One promising direction is to pose safety requirements as planning constraints in nonlinear, nonconvex optimization problems of motion synthesis. However, many implementations of this approach are limited by uncertain convergence and local optimality of the solutions achieved, affecting overall robustness. To improve upon these issues, we propose a novel two-stage optimization framework: In the first stage, we find a solution to a mixed-integer linear programming (MILP) formulation of the motion synthesis problem, the output of which initializes a second nonlinear programming (NLP) stage. The MILP stage enforces hard constraints of safety and road rule compliance generating a solution in the right subspace, while the NLP stage refines the solution within the safety bounds for feasibility and smoothness. We demonstrate the effectiveness of our framework via simulated experiments of complex urban driving scenarios, outperforming a state-of-the-art baseline in metrics of convergence, comfort, and progress.

Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between agents significantly decreases the number of trainable parameters, shortening training times to tractable levels, and has been linked to more efficient learning. However, having all agents share the same parameters can also have a detrimental effect on learning. We demonstrate the impact of parameter sharing methods on training speed and converged returns, establishing that when applied indiscriminately, their effectiveness is highly dependent on the environment. We propose a novel method to automatically identify agents which may benefit from sharing parameters by partitioning them based on their abilities and goals. Our approach combines the increased sample efficiency of parameter sharing with the representational capacity of multiple independent networks to reduce training time and increase final returns.

Ad hoc teamwork is the challenging problem of designing an autonomous agent which can adapt quickly to collaborate with teammates without prior coordination mechanisms, including joint training. Prior work in this area has focused on closed teams in which the number of agents is fixed. In this work, we consider open teams by allowing agents with different fixed policies to enter and leave the environment without prior notification. Our solution builds on graph neural networks to learn agent models and joint-action value models under varying team compositions. We contribute a novel action-value computation that integrates the agent model and joint-action value model to produce action-value estimates. We empirically demonstrate that our approach successfully models the effects other agents have on the learner, leading to policies that robustly adapt to dynamic team compositions and significantly outperform several alternative methods.

We propose an integrated prediction and planning system for autonomous driving which uses rational inverse planning to recognise the goals of other vehicles. Goal recognition informs a Monte Carlo Tree Search (MCTS) algorithm to plan optimal maneuvers for the ego vehicle. Inverse planning and MCTS utilise a shared set of defined maneuvers and macro actions to construct plans which are explainable by means of rationality principles. Evaluation in simulations of urban driving scenarios demonstrate the system’s ability to robustly recognise the goals of other vehicles, enabling our vehicle to exploit non-trivial opportunities to significantly reduce driving times. In each scenario, we extract intuitive explanations for the predictions which justify the system’s decisions.

It is important for autonomous vehicles to have the ability to infer the goals of other vehicles (goal recognition), in order to safely interact with other vehicles and predict their future trajectories. This is a difficult problem, especially in urban environments with interactions between many vehicles. Goal recognition methods must be fast to run in real time and make accurate inferences. As autonomous driving is safety- critical, it is important to have methods which are human interpretable and for which safety can be formally verified. Existing goal recognition methods for autonomous vehicles fail to satisfy all four objectives of being fast, accurate, interpretable and verifiable. We propose Goal Recognition with Interpre table Trees (GRIT), a goal recognition system which achieves these objectives. GRIT makes use of decision trees trained on vehicle trajectory data. We evaluate GRIT on two datasets, showing that GRIT achieved fast inference speed and comparable accuracy to two deep learning baselines, a planning-based goal recognition method, and an ablation of GRIT. We show that the learned trees are human interpretable and demonstrate how properties of GRIT can be formally verified using a satisfiability modulo theories (SMT) solver.

Recognising the goals or intentions of observed vehicles is a key step towards predicting the long-term future behaviour of other agents in an autonomous driving scenario. When there are unseen obstacles or occluded vehicles in a scenario, goal recognition may be confounded by the effects of these unseen entities on the behaviour of observed vehicles. Existing prediction algorithms that assume rational behaviour with respect to inferred goals may fail to make accurate long-horizon predictions because they ignore the possibility that the behaviour is influenced by such unseen entities. We introduce the Goal and Occluded Factor Inference (GOFI) algorithm which bases inference on inverse-planning to jointly infer a probabilistic belief over goals and potential occluded factors. We then show how these beliefs can be integrated into Monte Carlo Tree Search (MCTS). We demonstrate that jointly inferring goals and occluded factors leads to more accurate beliefs with respect to the true world state and allows an agent to safely navigate several scenarios where other baselines take unsafe actions leading to collisions.

Achieving a proper balance between planning quality, safety and efficiency is a major challenge for autonomous driving. Optimisation-based motion planners are capable of producing safe, smooth and comfortable plans, but often at the cost of runtime efficiency. On the other hand, naïvely deploying trajectories produced by efficient-to-run deep imitation learning approaches might risk compromising safety. In this paper, we present PILOT a planning framework that comprises an imitation neural network followed by an efficient optimiser that actively rectifies the network’s plan, guaranteeing fulfilment of safety and comfort requirements. The objective of the efficient optimiser is the same as the objective of an expensive-to-run optimisation-based planning system that the neural network is trained offline to imitate. This efficient optimiser provides a key layer of online protection from learning failures or deficiency in out-of-distribution situations that might compromise safety or comfort. Using a state-of-the-art, runtime-intensive optimisation-based method as the expert, we demonstrate in simulated autonomous driving experiments in CARLA that PILOT achieves a seven-fold reduction in runtime when compared to the expert it imitates without sacrificing planning quality.

Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled agents during execution. To eliminate this assumption, we extract representations from the local information of the controlled agent using encoder-decoder architectures. Using the observations and actions of the modelled agents during training, our models learn to extract representations about the modelled agents conditioned only on the local observations of the controlled agent. The representations are used to augment the controlled agent's decision policy which is trained via deep reinforcement learning; thus, during execution, the policy does not require access to other agents' information. We provide a comprehensive evaluation and ablations studies in cooperative, competitive and mixed multi-agent environments, showing that our method achieves significantly higher returns than baseline methods which do not use the learned representations.

Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm, called shared Experience Actor-Critic(SEAC), applies experience sharing in an actor-critic framework by combining the gradients of different agents. We evaluate SEAC in a collection of sparse-reward multi-agent environments and find that it consistently outperforms several baselines and state-of-the-art algorithms by learning in fewer steps and converging to higher returns. In some harder environments, experience sharing makes the difference between learning to solve the task and not learning at all.

Dynamic Bayesian networks (DBNs) are a general model for stochastic processes with partially observed states. Belief filtering in DBNs is the task of inferring the belief state (i.e. the probability distribution over process states) based on incomplete and uncertain observations. In this article, we explore the idea of accelerating the filtering task by automatically exploiting causality in the process. We consider a specific type of causal relation, called passivity, which pertains to how state variables cause changes in other variables. We present the Passivity-based Selective Belief Filtering (PSBF) method, which maintains a factored belief representation and exploits passivity to perform selective updates over the belief factors. PSBF is evaluated in both synthetic processes and a simulated multi-robot warehouse, where it outperformed alternative filtering methods by exploiting passivity.

Dynamic Bayesian networks (DBNs) are a general model for stochastic processes with partially observed states. Belief filtering in DBNs is the task of inferring the belief state (i.e. the probability distribution over process states) based on incomplete and noisy observations. This can be a hard problem in complex processes with large state spaces. In this article, we explore the idea of accelerating the filtering task by automatically exploiting causality in the process. We consider a specific type of causal relation, called passivity, which pertains to how state variables cause changes in other variables. We present the Passivity-based Selective Belief Filtering (PSBF) method, which maintains a factored belief representation and exploits passivity to perform selective updates over the belief factors. PSBF produces exact belief states under certain assumptions and approximate belief states otherwise, where the approximation error is bounded by the degree of uncertainty in the process. We show empirically, in synthetic processes with varying sizes and degrees of passivity, that PSBF is faster than several alternative methods while achieving competitive accuracy. Furthermore, we demonstrate how passivity occurs naturally in a complex system such as a multi-robot warehouse, and how PSBF can exploit this to accelerate the filtering task.

Many multiagent applications require an agent to learn quickly how to interact with previously unknown other agents. To address this problem, researchers have studied learning algorithms which compute posterior beliefs over a hypothesised set of policies, based on the observed actions of the other agents. The posterior belief is complemented by the prior belief, which specifies the subjective likelihood of policies before any actions are observed. In this paper, we present the first comprehensive empirical study on the practical impact of prior beliefs over policies in repeated interactions. We show that prior beliefs can have a significant impact on the long-term performance of such methods, and that the magnitude of the impact depends on the depth of the planning horizon. Moreover, our results demonstrate that automatic methods can be used to compute prior beliefs with consistent performance effects. This indicates that prior beliefs could be eliminated as a manual parameter and instead be computed automatically.