Bei Peng

activity

20172026

most citedCurriculum Learning for Reinforcement Learning Domains: A Framework and Survey

229 citations · 597 across the 19 of their papers we have counts for

collaborators

Showing 2021Show all

3 papers · 1 filter

cs.MA2021

SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments

Kai Liu, Yuyang Zhao, Gang Wang +1

Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degre…

cs.LG2021★ 1 cited

Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients

Bozhidar Vasilev, Tarun Gupta, Bei Peng +1

Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenari…

cs.LG2021★ 16 cited

Regularized Softmax Deep Multi-Agent $Q$ -Learning

Ling Pan, Tabish Rashid, Bei Peng +2

Tackling overestimation in $Q$ -learning is an important problem that has been extensively studied in single-agent reinforcement learning, but has received comparatively little atte…

SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments

Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients

Regularized Softmax Deep Multi-Agent Q-Learning

Regularized Softmax Deep Multi-Agent $Q$ -Learning