paper-with-me

Papers

Optimizing Multiagent Cooperation via Policy Evolution and Shared Experiences

2020-01-01 · ICML 2020 1 · Somdeb Majumdar, Shauharda Khadka, Santiago Miret, Stephen Mcaleer, Kagan Tumer

Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely on the team-based reward is often difficult due to its sparsity. Also, relying solely on the agent-specific reward is sub-optimal because it usually does not capture the team coordination objective. A common approach is to use reward shaping to construct a proxy reward by combining the individual rewards. However, this requires manual tuning for each environment. We introduce Multiagent Evolutionary Reinforcement Learning (MERL), a split-level training platform that handles the two objectives separately through two optimization processes. An evolutionary algorithm maximizes the sparse team-based objective through neuroevolution on a population of teams. Concurrently, a gradient-based optimizer trains policies to only maximize the dense agent-specific rewards. The gradient-based policies are periodically added to the evolutionary population as a way of information transfer between the two optimization processes. This enables the evolutionary algorithm to use skills learned via the agent-specific rewards toward optimizing the global objective. Results demonstrate that MERL significantly outperforms state-of-the-art methods, such as MADDPG, on a number of difficult coordination benchmarks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Towards Cooperation in Sequential Prisoner's Dilemmas: a Deep Multiagent Reinforcement Learning Approach

2018-03-01 · Weixun Wang, Jianye Hao, Yixi Wang, Matthew Taylor

The Iterated Prisoner's Dilemma has guided research on social dilemmas for decades. However, it distinguishes between only two atomic actions: cooperate and defect. In real-world prisoner's dilemmas, these choices are te…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning

2022-08-05 · Qingxu Fu, Tenghai Qiu, Zhiqiang Pu, Jianqiang Yi 외

Multiagent reinforcement learning (MARL) can solve complex cooperative tasks. However, the efficiency of existing MARL methods relies heavily on well-defined reward functions. Multiagent tasks with sparse reward feedback…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Learning Heterogeneous Agent Cooperation via Multiagent League Training

2022-11-13 · Qingxu Fu, Xiaolin Ai, Jianqiang Yi, Tenghai Qiu 외

Many multiagent systems in the real world include multiple types of agents with different abilities and functionality. Such heterogeneous multiagent systems have significant practical advantages. However, they also come …

Diversityreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Prioritized League Reinforcement Learning for Large-Scale Heterogeneous Multiagent Systems

2024-03-26 · Qingxu Fu, Zhiqiang Pu, Min Chen, Tenghai Qiu 외

Large-scale heterogeneous multiagent systems feature various realistic factors in the real world, such as agents with diverse abilities and overall system cost. In comparison to homogeneous systems, heterogeneous systems…

reinforcement-learningReinforcement Learning

An Efficient Application of Neuroevolution for Competitive Multiagent Learning

2021-05-23 · Unnikrishnan Rajendran Menon, Anirudh Rajiv Menon

Multiagent systems provide an ideal environment for the evaluation and analysis of real-world problems using reinforcement learning algorithms. Most traditional approaches to multiagent learning are affected by long trai…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)