Training autonomous agents to collaborate with unknown teammates in cooperative multi-agent environments remains a fundamental challenge in ad hoc teamwork research. Conventional approaches rely heavily on online interactions with arbitrary teammates under the assumption of full observability. However, in real-world scenarios, teammate policies are often inaccessible, making historical trajectory rollouts a more practical alternative. We propose DiTAC, a method that learns discrete teamwork abstractions for ad hoc collaboration by automatically extracting latent cooperation patterns from short trajectory segments and adapting effectively to diverse teammate behaviors. To mitigate the out-of-distribution challenge, we constrain learned representations within a discrete code-book. Furthermore, we employ a masked bidirectional transformer architecture to infer teammate behaviors from local observations, thereby relaxing the full observability assumption. Empirical results demonstrate that DiTAC significantly outperforms existing baselines and its variants across widely-used ad hoc teamwork tasks.

Despite their success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action spaces. To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i.e., using screenshots as input and keyboard and mouse actions as output. We introduce Cradle, a modular and flexible LMM-powered framework, as a preliminary attempt towards GCC. Enhanced by six key modules, Information Gathering, Self-Reflection, Task Inference, Skill Curation, Action Planning, and Memory, Cradle is able to understand input screenshots and output executable code for low-level keyboard and mouse control after high-level planning and information retrieval, so that Cradle can interact with any software and complete long-horizon complex tasks without relying on any built-in APIs. Experimental results show that Cradle exhibits remarkable generalizability and impressive performance across four previously unexplored commercial video games (Red Dead Redemption 2, Cities:Skylines, Stardew Valley and Dealer’s Life 2), five software applications (Chrome, Outlook, Feishu, Meitu and CapCut), and a comprehensive benchmark, OSWorld. With a unified interface to interact with any software, Cradle greatly extends the reach of foundation agents thus paving the way for generalist agents.

Recommendation models are predominantly trained using implicit user feedback, since explicit feedback is often costly to obtain. However, implicit feedback, such as clicks, does not always reflect users' real preferences. For example, a user might click on a news article because of its attractive headline, but end up feeling uncomfortable after reading the content. In the absence of explicit feedback, such erroneous implicit signals may severely mislead recommender systems. In this paper, we propose MTRec, a novel sequential recommendation framework designed to align with real user preferences by uncovering their internal satisfaction on recommended items. Specifically, we introduce a mental reward model to quantify user satisfaction and propose a distributional inverse reinforcement learning approach to learn it. The learned mental reward model is then used to guide recommendation models to better align with users’ real preferences. Our experiments show that MTRec brings significant improvements to a variety of recommendation models. We also deploy MTRec on an industrial short video platform and observe a 7\% increase in average user viewing time.

Reinforcement learning (RL) heavily depends on well-designed reward functions, which are often biased and difficult to design for complex behaviors. Preference-based RL (PbRL) addresses this by learning reward models from human feedback, but its practicality is constrained by a critical dilemma: while existing methods reduce human effort through query optimization, they neglect the preference buffer's restricted coverage — a factor that fundamentally determines the reliability of reward model. We systematically demonstrate this limitation creates distributional mismatch: reward models trained on static buffers reliably assess in-distribution trajectories but falter with out-of-distribution (OOD) trajectories from policy exploration. Crucially, such failures in policy-proximal regions directly misguide iterative policy updates. To address this, we propose **Proximal Policy Exploration (PPE)** with two key components: (1) a *proximal-policy extension* method that expands exploration in undersampled policy-proximal regions, and (2) a *mixture distribution query* method that balances in-distribution and OOD trajectory sampling. By enhancing buffer coverage while preserving evaluation accuracy in policy-proximal regions, PPE enables more reliable policy updates. Experiments across continuous control tasks demonstrate that PPE enhances preference feedback utilization efficiency and RL sample efficiency over baselines, highlighting preference buffer coverage management's vital role in PbRL.

Learning representations to capture the very fundamental understanding of the world is a key challenge in machine learning. The hierarchical structure of explanatory factors hidden in data is such a general representation and could be potentially achieved with a hierarchical VAE. However, training a hierarchical VAE always suffers from the “posterior collapse”, where the data information is hard to propagate to the higher-level latent variables, hence resulting in a bad hierarchical representation. To address this issue, we first analyze the shortcomings of existing methods for mitigating the posterior collapse from an information theory perspective, then highlight the necessity of regularization for explicitly propagating data information to higher-level latent variables while maintaining the dependency between different levels. This naturally leads to formulating the inference of the hierarchical latent representation as a sequential decision process, which could benefit from applying reinforcement learning (RL). Aligning RL's objective with the regularization, we first introduce a skip-generative path to acquire a reward for evaluating the information content of an inferred latent representation, and then the developed Q-value function based on it could have a consistent optimization direction of the regularization. Finally, policy gradient, one of the typical RL methods, is employed to train a hierarchical VAE without introducing a gradient estimator. Experimental results firmly support our analysis and demonstrate that our proposed method effectively mitigates the posterior collapse issue, learns an informative hierarchy, acquires explainable latent representations, and significantly outperforms other hierarchical VAE-based methods in downstream tasks.

Cooperative multi-agent reinforcement learning (MARL) is extensively used for solving complex cooperative tasks, and value decomposition methods are a prevalent approach for this domain. However, these methods have not been successful in addressing both homogeneous and heterogeneous tasks simultaneously which is a crucial aspect for the practical application of cooperative agents. On one hand, value decomposition methods demonstrate superior performance in homogeneous tasks. Nevertheless, they tend to produce agents with similar policies, which is unsuitable for heterogeneous tasks. On the other hand, solutions based on personalized observation or assigned roles are well-suited for heterogeneous tasks. However, they often lead to a trade-off situation where the agent's performance in homogeneous scenarios is negatively affected due to the aggregation of distinct policies. An alternative approach is to adopt sequential execution policies, which offer a flexible form for learning both types of tasks. However, learning sequential execution policies poses challenges in terms of credit assignment, and the limited information about subsequently executed agents can lead to sub-optimal solutions, which is known as the relative over-generalization problem. To tackle these issues, this paper proposes Greedy Sequential Execution (GSE) as a solution to learn the optimal policy that covers both scenarios. In the proposed GSE framework, we introduce an individual utility function into the framework of value decomposition to consider the complex interactions between agents. This function is capable of representing both the homogeneous and heterogeneous optimal policies. Furthermore, we utilize greedy marginal contribution calculated by the utility function as the credit value of the sequential execution policy to address the credit assignment and relative over-generalization problem. We evaluated GSE in both homogeneous and heterogeneous scenarios. The results demonstrate that GSE achieves significant improvement in performance across multiple domains, especially in scenarios involving both homogeneous and heterogeneous tasks.

Diffusion planners have shown promise in handling long-horizon and sparse-reward tasks due to the non-autoregressive plan generation. However, their inherent stochastic risk of generating infeasible trajectories presents significant challenges to their reliability and stability. We introduce a novel approach, the Trajectory Aggregation Tree (TAT), to address this issue in diffusion planners. Compared to prior methods that rely solely on raw trajectory predictions, TAT aggregates information from both historical and current trajectories, forming a dynamic tree-like structure. Each trajectory is conceptualized as a branch and individual states as nodes. As the structure evolves with the integration of new trajectories, unreliable states are marginalized, and the most impactful nodes are prioritized for decision-making. TAT can be deployed without modifying the original training and sampling pipelines of diffusion planners, making it a training-free, ready-to-deploy solution. We provide both theoretical analysis and empirical evidence to support TAT’s effectiveness. Our results highlight its remarkable ability to resist the risk from unreliable trajectories, guarantee the performance boosting of diffusion planners in 100% of tasks, and exhibit an appreciable tolerance margin for sample quality, thereby enabling planning with a more than $3\times$ acceleration.

Ad hoc teamwork requires an agent to cooperate with unknown teammates without prior coordination. Many works propose to abstract teammate instances into high-level representation of types and then pre-train the best response for each type. However, most of them do not consider the distribution of teammate instances within a type. This could expose the agent to the hidden risk of type confounding. In the worst case, the best response for an abstract teammate type could be the worst response for all specific instances of that type. This work addresses the issue from the lens of causal inference. We first theoretically demonstrate that this phenomenon is due to the spurious correlation brought by uncontrolled teammate distribution. Then, we propose our solution, CTCAT, which disentangles such correlation through an instance-wise teammate feedback rectification. This operation reweights the interaction of teammate instances within a shared type to reduce the influence of type confounding. The effect of CTCAT is evaluated in multiple domains, including classic ad hoc teamwork tasks and real-world scenarios. Results show that CTCAT is robust to the influence of type confounding, a practical issue that directly hazards the robustness of our trained agents but was unnoticed in previous works.

Offline Reinforcement Learning (RL) has demonstrated promising results in various applications by learning policies from previously collected datasets, reducing the need for online exploration and interactions. However, real-world scenarios usually involve partial observability, which brings crucial challenges of the deployment of offline RL methods: i) the policy trained on data with full observability is not robust against the masked observations during execution, and ii) the information of which parts of observations are masked is usually unknown during training. In order to address these challenges, we present Offline RL with DiscrEte pRoxy representations (ORDER), a probabilistic framework which leverages novel state representations to improve the robustness against diverse masked observabilities. Specifically, we propose a discrete representation of the states and use a proxy representation to recover the states from masked partial observable trajectories. The training of ORDER can be compactly described as the following three steps. i) Learning the discrete state representations on data with full observations, ii) Training the decision module based on the discrete representations, and iii) Training the proxy discrete representations on the data with various partial observations, aligning with the discrete representations. We conduct extensive experiments to evaluate ORDER, showcasing its effectiveness in offline RL for diverse partially observable scenarios and highlighting the significance of discrete proxy representations in generalization performance. ORDER is a flexible framework to employ any offline RL algorithms and we hope that ORDER can pave the way for the deployment of RL policy against various partial observabilities in the real world.

Offline reinforcement learning is a promising approach for practical applications since it does not require interactions with real-world environments. However, existing offline RL methods only work well in environments with continuous or small discrete action spaces. In environments with large and discrete action spaces, such as recommender systems and dialogue systems, the performance of existing methods decreases drastically because they suffer from inaccurate value estimation for a large proportion of out-of-distribution (o.o.d.) actions. While recent works have demonstrated that online RL benefits from incorporating semantic information in action representations, unfortunately, they fail to learn reasonable relative distances between action representations, which is key to offline RL to reduce the influence of o.o.d. actions. This paper proposes an action representation learning framework for offline RL based on a pseudometric, which measures both the behavioral relation and the data-distributional relation between actions. We provide theoretical analysis on the continuity of the expected Q-values and the offline policy improvement using the learned action representations. Experimental results show that our methods significantly improve the performance of two typical offline RL methods in environments with large and discrete action spaces.

In recent years, the learning of deep spiking neural networks(SNN) has attracted increasing researchers' interest, and has also made important progresses in theories and applications. It is desired to choose a neuron model with biological features and suitable for SNN training. Currently, Leaky Integrate-and-Fire(LIF) model is mainly used in deep SNN and some factors that can express the spatio-temporal information are ignored in the model. In this work, inspired by the Hodgkin-Huxley(H-H) model, we propose an improved LIF neuron model, which is an iterative current-based LIF model with voltage-based variable resistance. The improved neuron model is closer to the characteristics of the biological neuron model, which can make use of the spatio-temporal information. We further construct a new SNN learning algorithm that uses spatio-temporal back propagation by defining a loss function. We evaluated the proposed methods on single-label and multi-label data sets. The experimental results show that the variable resistance of the neuron model will affect the performance of the model. Choosing the appropriate relationship between the variable resistance and the membrane voltage can effectively improve the recognition accuracy.

The temporal credit assignment problem, which aims to discover the predictive features hidden in distracting background streams with delayed feedback, remains a core challenge in biological and machine learning. To address this issue, we propose a novel spatio-temporal credit assignment algorithm called STCA for training deep spiking neural networks (DSNNs). We present a new spatiotemporal error backpropagation policy by defining a temporal based loss function, which is able to credit the network losses to spatial and temporal domains simultaneously. Experimental results on MNIST dataset and a music dataset (MedleyDB) demonstrate that STCA can achieve comparable performance with other state-of-the-art algorithms with simpler architectures. Furthermore, STCA successfully discovers predictive sensory features and shows the highest performance in the unsegmented sensory event detection tasks.