SIDE: I Infer the State I Want to Learn

05/13/2021
by   Zhiwei Xu, et al.
0

As one of the solutions to the Dec-POMDP problem, the value decomposition method has achieved good results recently. However, most value decomposition methods require the global state during training, but this is not feasible in some scenarios where the global state cannot be obtained. Therefore, we propose a novel value decomposition framework, named State Inference for value DEcomposition (SIDE), which eliminates the need to know the true state by simultaneously seeking solutions to the two problems of optimal control and state inference. SIDE can be extended to any value decomposition method, as well as other types of multi-agent algorithms in the case of Dec-POMDP. Based on the performance results of different algorithms in Starcraft II micromanagement tasks, we verified that SIDE can construct the current state that contributes to the reinforcement learning process based on past local observations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2022

Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning

Recently, model-based agents have achieved better performance than model...
research
06/22/2021

MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning

In the real world, many tasks require multiple agents to cooperate with ...
research
02/04/2023

Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative Multi-Agent Reinforcement Learning

Value decomposition methods have gradually become popular in the coopera...
research
05/31/2020

Towards Understanding Linear Value Decomposition in Cooperative Multi-Agent Q-Learning

Value decomposition is a popular and promising approach to scaling up mu...
research
09/20/2022

Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning

In cooperative multi-agent reinforcement learning, centralized training ...
research
06/29/2020

Exploring Optimal Control With Observations at a Cost

There has been a current trend in reinforcement learning for healthcare ...
research
02/10/2020

Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning

In many real-world settings, a team of cooperative agents must learn to ...

Please sign up or login with your details

Forgot password? Click here to reset