相关论文: COSAC: Counterfactual Credit Assignment in Sequent…

One of the key challenges for multi-agent learning is scalability. In this paper, we introduce a technique for speeding up multi-agent learning by exploiting concurrent and incremental experience sharing. This solution adaptively identifies…

Traditional Reinforcement Learning (RL) policies are typically implemented with fixed control rates, often disregarding the impact of control rate selection. This can lead to inefficiencies as the optimal control rate varies with task…

Reinforcement learning (RL) for large language models (LLMs) increasingly relies on sparse, outcome-level rewards -- yet determining which actions within a long trajectory caused the outcome remains difficult. This credit assignment (CA)…

Actor-critic (AC) methods are widely used in reinforcement learning (RL) and benefit from the flexibility of using any policy gradient method as the actor and value-based method as the critic. The critic is usually trained by minimizing the…

Cooperative artificial intelligence with human or superhuman proficiency in collaborative tasks stands at the frontier of machine learning research. Prior work has tended to evaluate cooperative AI performance under the restrictive…

Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of agents. In this paper,…

Cooperative multi-agent decision making involves a group of agents cooperatively solving learning problems while communicating over a network with delays. In this paper, we consider the kernelised contextual bandit problem, where the reward…

Achieving cooperation among self-interested agents remains a fundamental challenge in multi-agent reinforcement learning. Recent work showed that mutual cooperation can be induced between "learning-aware" agents that account for and shape…

Communication can improve coordination in partially observed multi-agent reinforcement learning (MARL), but learning \emph{when} and \emph{who} to communicate with requires choosing among many possible sender-recipient pairs, and the effect…

Soft Actor-Critic (SAC) is one of the state-of-the-art off-policy reinforcement learning (RL) algorithms that is within the maximum entropy based RL framework. SAC is demonstrated to perform very well in a list of continous control tasks…

Actor-critic methods, a type of model-free reinforcement learning (RL), have achieved state-of-the-art performances in many real-world domains in continuous control. Despite their success, the wide-scale deployment of these models is still…

This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel. We focus on improving information sharing between agents and…

This work addresses competitive resource allocation in a sequential setting, where two players allocate resources across objects or locations of shared interest. Departing from the simultaneous Colonel Blotto game, our framework introduces…

We present temporally abstract actor-critic (TAAC), a simple but effective off-policy RL algorithm that incorporates closed-loop temporal abstraction into the actor-critic framework. TAAC adds a second-stage binary policy to choose between…

In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structured representations…

Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we formulate the RL…

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,…

The overestimation bias is one of the major impediments to accurate off-policy learning. This paper investigates a novel way to alleviate the overestimation bias in a continuous control setting. Our method---Truncated Quantile Critics,…

Model-free deep reinforcement learning (RL) has been successfully applied to challenging continuous control domains. However, poor sample efficiency prevents these methods from being widely used in real-world domains. This paper introduces…

Task allocation can enable effective coordination of multi-robot teams to accomplish tasks that are intractable for individual robots. However, existing approaches to task allocation often assume that task requirements or reward functions…