Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning

14 Apr 2021  ยท  Yuan Pu, Shaochen Wang, Rui Yang, Xin Yao, Bin Li ยท

Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks. Two main promising research directions are multi-agent value function decomposition and multi-agent policy gradients. In this paper, we propose a new decomposed multi-agent soft actor-critic (mSAC) method, which effectively combines the advantages of the aforementioned two methods. The main modules include decomposed Q network architecture, discrete probabilistic policy and counterfactual advantage function (optinal). Theoretically, mSAC supports efficient off-policy learning and addresses credit assignment problem partially in both discrete and continuous action spaces. Tested on StarCraft II micromanagement cooperative multiagent benchmark, we empirically investigate the performance of mSAC against its variants and analyze the effects of the different components. Experimental results demonstrate that mSAC significantly outperforms policy-based approach COMA, and achieves competitive results with SOTA value-based approach Qmix on most tasks in terms of asymptotic perfomance metric. In addition, mSAC achieves pretty good results on large action space tasks, such as 2c_vs_64zg and MMM2.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
SMAC+ Def_Armored_parallel MASAC Median Win Rate 0.0 # 6
SMAC+ Def_Armored_sequential MASAC Median Win Rate 0.0 # 9
SMAC+ Def_Infantry_parallel MASAC Median Win Rate 30.0 # 9
SMAC+ Def_Infantry_sequential MASAC Median Win Rate 37.5 # 10
SMAC+ Def_Outnumbered_parallel MASAC Median Win Rate 0.0 # 4
SMAC+ Def_Outnumbered_sequential MASAC Median Win Rate 0.0 # 5
SMAC+ Off_Complicated_parallel MASAC Median Win Rate 0.0 # 4
SMAC+ Off_Distant_parallel MASAC Median Win Rate 0.0 # 3
SMAC+ Off_Hard_parallel MASAC Median Win Rate 0.0 # 3
SMAC+ Off_Near_parallel MASAC Median Win Rate 0.0 # 6
SMAC+ Off_Superhard_parallel MASAC Median Win Rate 0.0 # 1

Methods


No methods listed for this paper. Add relevant methods here