In recent years, Multi-Agent Reinforcement Learning (MARL) techniques have made significant strides in achieving high asymptotic performance in single task. However, there has been limited exploration of model transferability across tasks. Training a model from scratch for each task can be time-consuming and expensive, especially for large-scale Multi-Agent Systems. Therefore, it is crucial to develop methods for generalizing the model across tasks. Considering that there exist task-independent subtasks across MARL tasks, a model that can decompose such subtasks from the source task could generalize to target tasks.

Reaching consensus and convergence to equilibrium are two major challenges of multi-agent systems. Although each has attracted significant attention, relatively few studies address both challenges at the same time. This paper examines the connection between the notions of consensus and equilibrium in a multi-agent system where multiple interacting sub-populations coexist. We argue that consensus can be seen as an intricate component of intra-population stability, whereas equilibrium can be seen as encoding inter-population stability. We show that smooth fictitious play, a well-known learning model in game theory, can achieve both consensus and convergence to equilibrium in diverse multi-agent settings.

Cooperative multi-agent reinforcement learning (MARL) is a challenging task, as agents must learn complex and diverse individual strategies from a shared team reward. However, existing methods struggle to distinguish and exploit important individual experiences, as they lack an effective way to decompose the team reward into individual rewards. To address this challenge, we propose DIFFER, a powerful theoretical framework for decomposing individual rewards to enable fair experience replay in MARL.By enforcing the invariance of network gradients, we establish a partial differential equation whose solution yields the underlying individual reward function. The individual TD-error can then be computed from the solved closed-form individual rewards, indicating the importance of each piece of experience in the learning task and guiding the training process. Our method elegantly achieves an equivalence to the original learning framework when individual experiences are homogeneous, while also adapting to achieve more muscular efficiency and fairness when diversity is observed.Our extensive experiments on popular benchmarks validate the effectiveness of our theory and method, demonstrating significant improvements in learning efficiency and fairness. Code is available in supplement material.

Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their problem-solving capabilities. To address this, we propose a dual self-awareness value decomposition framework, inspired by the notion of dual self-awareness in psychology, that entirely rejects the IGM premise. Each agent consists of an ego policy for action selection and an alter ego value function to solve the credit assignment problem. The value function factorization can ignore the IGM assumption by utilizing an explicit search procedure.

One of the main challenges in offline Reinforcement Learning (RL) is the distribution shift that arises from the learned policy deviating from the data collection policy. This is often addressed by avoiding out-of-distribution (OOD) actions during policy improvement as their presence can lead to substantial performance degradation. This challenge is amplified in the offline Multi-Agent RL (MARL) setting since the joint action space grows exponentially with the number of agents.To avoid this curse of dimensionality, existing MARL methods adopt either value decomposition methods or fully decentralized training of individual agents. However, even when combined with standard conservatism principles, these methods can still result in the selection of OOD joint actions in offline MARL. To this end, we introduce AlberDICE,an offline MARL algorithm that alternatively performs centralized training of individual agents based on stationary distribution optimization. AlberDICE circumvents the exponential complexity of MARL by computing the best response of one agent at a time while effectively avoiding OOD joint action selection.

We study the problem of regret minimization in Multi-Agent Multi-Armed Bandits (MAMABs) where the rewards are defined through a factor graph. We derive an instance-specific regret lower bound and characterize the minimal expected number of times each global action should be explored. Unfortunately, this bound and the corresponding optimal exploration process are obtained by solving a combinatorial optimization problem with a set of variables and constraints exponentially growing with the number of agents. We approximate the regret lower bound problem via Mean Field techniques to reduce the number of variables and constraints. By tuning the latter, we explore the trade-off between achievable regret and complexity.

In a multi-agent system, one may choose to govern the behaviour of an agent by imposing norms, which act as guidelines for how agents should act either all of the time or in given situations. However, imposing multiple norms on one or more agents may result in situations where these norms conflict over how the agent should behave. In any system with normative conflicts (such as safe reinforcement models or systems which monitor safety protocols), one must decide which norms should be followed such that the most important and most relevant norms are maintained. We introduce a new method for resolving normative conflicts through argumentation and graph colouring which is compatible with a variety of normative conflict resolution policies. We prove that this method always creates an admissible set of arguments under argumentation semantics, meaning that it produces coherent outputs. We also introduce more robust variants of this method, each building upon their predecessor to create a superior output, and we include further mathematical proof of their coherence. Our most advanced variant uses the existing concept of curtailment, where one norm may supersede another without fully eliminating it. The methods we introduce are all compatible with various pre-existing policies for resolving normative conflicts. Empirical evaluations are also performed to compare our algorithms to each other and to others in existing literature.

Large Language Models (LLMs) agents are increasingly pivotal for addressing complex tasks in interactive environments. Existing work mainly focuses on enhancing performance through behavior cloning from stronger experts, yet such approaches often falter in real-world applications, mainly due to the inability to recover from errors. However, step-level critique data is difficult and expensive to collect. Automating and dynamically constructing self-critique datasets is thus crucial to empowering models with intelligent agent capabilities. In this work, we propose an iterative self-training framework, Agent-R, that enables language Agent to Reflect on the fly. Unlike traditional methods that reward or penalize actions based on correctness, Agent-R leverages MCTS to construct training data that recover correct trajectories from erroneous ones. A key challenge of agent reflection lies in the necessity for timely revision rather than waiting until the end of a rollout. To address this, we introduce a model-guided critique construction mechanism: the actor model identifies the first error step (within its current capability) in a failed trajectory. Starting from it, we splice it with the adjacent correct path, which shares the same parent node in the tree. This strategy enables the model to learn reflection based on its current policy, therefore yielding better learning efficiency. To further explore the scalability of this self-improvement paradigm, we investigate iterative refinement of both error correction capabilities and dataset construction. Our findings demonstrate that Agent-R continuously improves the model's ability to recover from errors and enables timely error correction. Experiments on three interactive environments show that Agent-R effectively equips agents to correct erroneous actions while avoiding loops, achieving superior performance compared to baseline methods (+5.59%).

Multi-agent reinforcement learning (MARL) has primarily focused on solving a single task in isolation, while in practice the environment is often evolving, leaving many related tasks to be solved. In this paper, we investigate the benefits of meta-learning in solving multiple MARL tasks collectively. We establish the first line of theoretical results for meta-learning in a wide range of fundamental MARL settings, including learning Nash equilibria in two-player zero-sum Markov games and Markov potential games, as well as learning coarse correlated equilibria in general-sum Markov games. Under natural notions of task similarity, we show that meta-learning achieves provable sharper convergence to various game-theoretical solution concepts than learning each task separately. As an important intermediate step, we develop multiple MARL algorithms with initialization-dependent convergence guarantees.

Embodied agents operate in a structured world, often solving tasks with spatial, temporal, and permutation symmetries. Most algorithms for planning and model-based reinforcement learning (MBRL) do not take this rich geometric structure into account, leading to sample inefficiency and poor generalization. We introduce the Equivariant Diffuser for Generating Interactions (EDGI), an algorithm for MBRL and planning that is equivariant with respect to the product of the spatial symmetry group SE(3), the discrete-time translation group ℤ, and the object permutation group Sₙ. EDGI follows the Diffuser framework by Janner et al. (2022) in treating both learning a world model and planning in it as a conditional generative modeling problem, training a diffusion model on an offline trajectory dataset. We introduce a new SE(3) ℤ Sₙ-equivariant diffusion model that supports multiple representations.