Off-Policy Correction For Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2111.11229v3
• Date: Wed, 3 Apr 2024 17:13:05 GMT
• Title: Off-Policy Correction For Multi-Agent Reinforcement Learning
• Authors: Michał Zawalski, Błażej Osiński, Henryk Michalewski, Piotr Miłoś,
• Abstract summary: Multi-agent reinforcement learning (MARL) provides a framework for problems involving multiple interacting agents. Despite apparent similarity to the single-agent case, multi-agent problems are often harder to train and analyze theoretically. We propose MA-Trace, a new on-policy actor-critic algorithm, which extends V-Trace to the MARL setting.
• Score: 9.599347559588216
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent reinforcement learning (MARL) provides a framework for problems involving multiple interacting agents. Despite apparent similarity to the single-agent case, multi-agent problems are often harder to train and analyze theoretically. In this work, we propose MA-Trace, a new on-policy actor-critic algorithm, which extends V-Trace to the MARL setting. The key advantage of our algorithm is its high scalability in a multi-worker setting. To this end, MA-Trace utilizes importance sampling as an off-policy correction method, which allows distributing the computations with no impact on the quality of training. Furthermore, our algorithm is theoretically grounded - we prove a fixed-point theorem that guarantees convergence. We evaluate the algorithm extensively on the StarCraft Multi-Agent Challenge, a standard benchmark for multi-agent algorithms. MA-Trace achieves high performance on all its tasks and exceeds state-of-the-art results on some of them.

Related papers

• Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer [62.01554688056335]
  Overestimation in the multiagent setting has received comparatively little attention. We propose a novel hypernet regularizer on hypernetwork weights and biases to constrain the optimization of online global Q-network to prevent overestimation accumulation.
  arXiv  Detail & Related papers  (2025-02-04T05:14:58Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [64.13803241218886]
  We present a first step toward "Multi-agent LLM training" (MALT) on reasoning problems. Our approach employs a sequential multi-agent setup with heterogeneous LLMs assigned specialized roles. We evaluate our approach across MATH, GSM8k, and CQA, where MALT on Llama 3.1 8B models achieves relative improvements of 14.14%, 7.12%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• Exploring Multi-Agent Reinforcement Learning for Unrelated Parallel Machine Scheduling [2.3034630097498883]
  The study introduces the Reinforcement Learning environment and conducts empirical analyses. The experiments employ various deep neural network policies for single- and Multi-Agent approaches. While Single-Agent algorithms perform adequately in reduced scenarios, Multi-Agent approaches reveal challenges in cooperative learning but a scalable capacity.
  arXiv  Detail & Related papers  (2024-11-12T08:27:27Z)
• Inverse Factorized Q-Learning for Cooperative Multi-agent Imitation Learning [13.060023718506917]
  imitation learning (IL) is a problem of learning to mimic expert behaviors from demonstrations in cooperative multi-agent systems. We introduce a novel multi-agent IL algorithm designed to address these challenges. Our approach enables the centralized learning by leveraging mixing networks to aggregate decentralized Q functions.
  arXiv  Detail & Related papers  (2023-10-10T17:11:20Z)
• Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing [11.639503711252663]
  We tackle the multi-agent active hypothesis testing (AHT) problem by introducing a novel algorithm rooted in the framework of deep multi-agent reinforcement learning. We present a comprehensive set of experimental results that effectively showcase the agents' ability to learn collaborative strategies and enhance performance.
  arXiv  Detail & Related papers  (2023-09-14T01:18:04Z)
• MADiff: Offline Multi-agent Learning with Diffusion Models [79.18130544233794]
  MADiff is a diffusion-based multi-agent learning framework. It works as both a decentralized policy and a centralized controller. Our experiments demonstrate that MADiff outperforms baseline algorithms across various multi-agent learning tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:14:09Z)
• The Multi-Agent Pickup and Delivery Problem: MAPF, MARL and Its Warehouse Applications [2.969705152497174]
  We study two state-of-the-art solutions to the multi-agent pickup and delivery problem based on different principles. Specifically, a recent MAPF algorithm called conflict-based search (CBS) and a current MARL algorithm called shared experience actor-critic (SEAC) are studied.
  arXiv  Detail & Related papers  (2022-03-14T13:23:35Z)
• Softmax with Regularization: Better Value Estimation in Multi-Agent Reinforcement Learning [72.28520951105207]
  Overestimation in $Q$-learning is an important problem that has been extensively studied in single-agent reinforcement learning. We propose a novel regularization-based update scheme that penalizes large joint action-values deviating from a baseline. We show that our method provides a consistent performance improvement on a set of challenging StarCraft II micromanagement tasks.
  arXiv  Detail & Related papers  (2021-03-22T14:18:39Z)
• 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)
• Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic [54.2180984002807]
  Multi-agent adversarial inverse reinforcement learning (MA-AIRL) is a recent approach that applies single-agent AIRL to multi-agent problems. We propose a multi-agent inverse RL algorithm that is more sample-efficient and scalable than previous works.
  arXiv  Detail & Related papers  (2020-02-24T20:30:45Z)

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.