paper-with-me

홈 › Papers

Credit-cognisant reinforcement learning for multi-agent cooperation

2022-11-18 · F. Bredell, H. A. Engelbrecht, J. C. Schoeman

Traditional multi-agent reinforcement learning (MARL) algorithms, such as independent Q-learning, struggle when presented with partially observable scenarios, and where agents are required to develop delicate action sequences. This is often the result of the reward for a good action only being available after other agents have taken theirs, and these actions are not credited accordingly. Recurrent neural networks have proven to be a viable solution strategy for solving these types of problems, resulting in significant performance increase when compared to other methods. In this paper, we explore a different approach and focus on the experiences used to update the action-value functions of each agent. We introduce the concept of credit-cognisant rewards (CCRs), which allows an agent to perceive the effect its actions had on the environment as well as on its co-agents. We show that by manipulating these experiences and constructing the reward contained within them to include the rewards received by all the agents within the same action sequence, we are able to improve significantly on the performance of independent deep Q-learning as well as deep recurrent Q-learning. We evaluate and test the performance of CCRs when applied to deep reinforcement learning techniques at the hands of a simplified version of the popular card game Hanabi.

📄 PDF Abstract BibTeX arXiv:2211.10100

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningMulti-agent Reinforcement LearningQ-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Test 설명 없음
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning

2022-06-02 · Hao Chen, Guangkai Yang, Junge Zhang, Qiyue Yin 외

In recent years, reinforcement learning has faced several challenges in the multi-agent domain, such as the credit assignment issue. Value function factorization emerges as a promising way to handle the credit assignment…

Deep Reinforcement LearningReinforcement Learning (RL)RelationZero-shot Generalization

CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning

2018-09-13 · ICLR 2020 1 · Jiachen Yang, Alireza Nakhaei, David Isele, Kikuo Fujimura 외

A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, whi…

Autonomous VehiclesEfficient ExplorationMulti-agent Reinforcement Learningreinforcement-learning+2

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)

MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation

2026-07-30 · Dawei Wang, Di Zhao, Xinyuan Liu, Marci Chi Ma 외 arxiv

Credit assignment is a fundamental challenge in cooperative multi-agent reinforcement learning, particularly in embodied AI settings characterized by limited and delayed feedback as well as dynamically changing numbers o…

Multi-agent Reinforcement Learning

Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning

2022-09-10 · Yunxiao Guo, Xinjia Xie, Runhao Zhao, Chenglan Zhu 외

Flocking is a very challenging problem in a multi-agent system; traditional flocking methods also require complete knowledge of the environment and a precise model for control. In this paper, we propose Evolutionary Mult…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)