Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2110.08642v1
• Date: Sat, 16 Oct 2021 19:03:34 GMT
• Title: Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning
• Authors: Yuchen Xiao, Xueguang Lyu, Christopher Amato
• Abstract summary: We propose a new multi-agent policy gradient method called Robust Local Advantage (ROLA) Actor-Critic. ROLA allows each agent to learn an individual action-value function as a local critic as well as ameliorating environment non-stationarity. We show ROLA's robustness and effectiveness over a number of state-of-the-art multi-agent policy gradient algorithms.
• Score: 19.519440854957633
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Policy gradient methods have become popular in multi-agent reinforcement learning, but they suffer from high variance due to the presence of environmental stochasticity and exploring agents (i.e., non-stationarity), which is potentially worsened by the difficulty in credit assignment. As a result, there is a need for a method that is not only capable of efficiently solving the above two problems but also robust enough to solve a variety of tasks. To this end, we propose a new multi-agent policy gradient method, called Robust Local Advantage (ROLA) Actor-Critic. ROLA allows each agent to learn an individual action-value function as a local critic as well as ameliorating environment non-stationarity via a novel centralized training approach based on a centralized critic. By using this local critic, each agent calculates a baseline to reduce variance on its policy gradient estimation, which results in an expected advantage action-value over other agents' choices that implicitly improves credit assignment. We evaluate ROLA across diverse benchmarks and show its robustness and effectiveness over a number of state-of-the-art multi-agent policy gradient algorithms.

Related papers

• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning [139.53668999720605]
  We present a multi-agent PPO algorithm in which the local policy of each agent is updated similarly to vanilla PPO. We prove that with standard regularity conditions on the Markov game and problem-dependent quantities, our algorithm converges to the globally optimal policy at a sublinear rate.
  arXiv  Detail & Related papers  (2023-05-08T16:20:03Z)
• Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction [12.94372063457462]
  Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. It suffers from a critical drawback due to its reliance on learning from a single sample of the joint-action at a given state. We propose an enhancement tool that accommodates any actor-critic MARL method.
  arXiv  Detail & Related papers  (2022-09-02T13:44:00Z)
• Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling [13.915157044948364]
  One of the preeminent obstacles to scaling multi-agent reinforcement learning is assigning credit to individual agents' actions. In this paper, we address this credit assignment problem with an approach that we call textitpartial reward decoupling (PRD) PRD decomposes large cooperative multi-agent RL problems into decoupled subproblems involving subsets of agents, thereby simplifying credit assignment.
  arXiv  Detail & Related papers  (2021-12-23T17:48:04Z)
• Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction [73.77593805292194]
  We train a separate exploration policy to maximize an approximate upper confidence bound of the critics in an off-policy actor-critic framework. To mitigate the off-policy-ness, we adapt the recently introduced DICE framework to learn a distribution correction ratio for off-policy actor-critic training.
  arXiv  Detail & Related papers  (2021-10-22T22:07:51Z)
• Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning [52.7873574425376]
  Cooperative multi-agent reinforcement learning (MARL) faces significant scalability issues due to state and action spaces that are exponentially large in the number of agents. We propose a novel, value-based multi-agent algorithm called LOMAQ, which incorporates local rewards in the Training Decentralized Execution paradigm.
  arXiv  Detail & Related papers  (2021-09-22T10:08:15Z)
• DSDF: An approach to handle stochastic agents in collaborative multi-agent reinforcement learning [0.0]
  We show how thisity of agents, which could be a result of malfunction or aging of robots, can add to the uncertainty in coordination. Our solution, DSDF which tunes the discounted factor for the agents according to uncertainty and use the values to update the utility networks of individual agents.
  arXiv  Detail & Related papers  (2021-09-14T12:02:28Z)
• Policy Gradient Bayesian Robust Optimization for Imitation Learning [49.881386773269746]
  We derive a novel policy gradient-style robust optimization approach, PG-BROIL, to balance expected performance and risk. Results suggest PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse.
  arXiv  Detail & Related papers  (2021-06-11T16:49:15Z)
• Scalable, Decentralized Multi-Agent Reinforcement Learning Methods Inspired by Stigmergy and Ant Colonies [0.0]
  We investigate a novel approach to decentralized multi-agent learning and planning. In particular, this method is inspired by the cohesion, coordination, and behavior of ant colonies. The approach combines single-agent RL and an ant-colony-inspired decentralized, stigmergic algorithm for multi-agent path planning and environment modification.
  arXiv  Detail & Related papers  (2021-05-08T01:04:51Z)
• FACMAC: Factored Multi-Agent Centralised Policy Gradients [103.30380537282517]
  We propose FACtored Multi-Agent Centralised policy gradients (FACMAC) It is a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces. We evaluate FACMAC on variants of the multi-agent particle environments, a novel multi-agent MuJoCo benchmark, and a challenging set of StarCraft II micromanagement tasks.
  arXiv  Detail & Related papers  (2020-03-14T21:29:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.