相关论文: Factored Value Functions for Graph-Based Multi-Age…

Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Moreover, scalar…

In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features…

Multi-agent reinforcement learning tasks put a high demand on the volume of training samples. Different from its single-agent counterpart, distributed value-based multi-agent reinforcement learning faces the unique challenges of demanding…

In graph-structured multi-agent reinforcement learning (MARL) adversarial tasks such as pursuit and confrontation, agents must coordinate under highly dynamic interactions, where sparse rewards hinder efficient policy learning. We propose…

Tackling multi-agent learning problems efficiently is a challenging task in continuous action domains. While value-based algorithms excel in sample efficiency when applied to discrete action domains, they are usually inefficient when…

Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution, where value-factorization methods enforce the individual-global-maximum (IGM) principle so that decentralized greedy…

Multi-scene reinforcement learning involves training the RL agent across multiple scenes / levels from the same task, and has become essential for many generalization applications. However, the inclusion of multiple scenes leads to an…

Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However,…

We study real-time sampling and estimation of autoregressive Markovian sources in decentralized and dynamic multi-hop networks that share similar structures. Nodes cache neighboring samples and communicate over wireless collision channels.…

This paper addresses the challenge of decentralized task allocation within heterogeneous multi-agent systems operating under communication constraints. We introduce a novel framework that integrates graph neural networks (GNNs) with a…

General value functions (GVFs) in the reinforcement learning (RL) literature are long-term predictive summaries of the outcomes of agents following specific policies in the environment. Affordances as perceived action possibilities with…

Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons, and standard RL methods provide too few tools to provide insight into the…

Value factorization, a popular paradigm in MARL, faces significant theoretical and algorithmic bottlenecks: its tendency to converge to suboptimal solutions remains poorly understood and unsolved. Theoretically, existing analyses fail to…

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…

In multi-agent reinforcement learning systems, the actions of one agent can have a negative impact on the rewards of other agents. One way to combat this problem is to let agents trade their rewards amongst each other. Motivated by this,…

Existing asynchronous MARL methods based on MacDec-POMDP typically construct training trajectory buffers by simply sampling limited and biased data at the endpoints of macro-actions, and directly apply conventional MARL methods on the…

Centralized training with decentralized execution (CTDE) has been the dominant paradigm in multi-agent reinforcement learning (MARL), but its reliance on global state information during training introduces scalability, robustness, and…

Reward decomposition is a critical problem in centralized training with decentralized execution~(CTDE) paradigm for multi-agent reinforcement learning. To take full advantage of global information, which exploits the states from all agents…

We introduce a distributional method for learning the optimal policy in risk averse Markov decision process with finite state action spaces, latent costs, and stationary dynamics. We assume sequential observations of states, actions, and…

We study multi-agent reinforcement learning (MARL) in a stochastic network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in this setting because…