mlsanityData to 14 Oct 2026

Latent Interactive A2C for Improved RL in Open Many-Agent Systems

arXiv 2305.05159 ↗First posted 9 May 2023cs.LG cs.AI cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

There is a prevalence of multiagent reinforcement learning (MARL) methods that engage in centralized training. But, these methods involve obtaining various types of information from the other agents, which may not be feasible in competitive or adversarial settings. A recent method, the interactive advantage actor critic (IA2C), engages in decentralized training coupled with decentralized execution, aiming to predict the other agents' actions from possibly noisy observations. In this paper, we present the latent IA2C that utilizes an encoder-decoder architecture to learn a latent representation of the hidden state and other agents' actions. Our experiments in two domains -- each populated by many agents -- reveal that the latent IA2C significantly improves sample efficiency by reducing variance and converging faster. Additionally, we introduce open versions of these domains where the agent population may change over time, and evaluate on these instances as well.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 9 May 2023.

Builds on

12 of 22 references.

References · 12

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  2. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  3. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  4. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  5. 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 231
  6. 2017Learning with Opponent-Learning Awarenesscited by 222
  7. 2017MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligencecited by 71
  8. 2020Agent Modelling under Partial Observability for Deep Reinforcement Learningcited by 57
  9. 2020Towards Open Ad Hoc Teamwork Using Graph-based Policy Learningcited by 37
  10. 2019Scalable Decision-Theoretic Planning in Open and Typed Multiagent Systemscited by 7
  11. 2021SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learningcited by 7
  12. 2020Cooperative-Competitive Reinforcement Learning with History-Dependent Rewardscited by 3

Built on by

Not cited yet.