Shaping Advice in Deep Multi-Agent Reinforcement Learning

by   Baicen Xiao, et al.

Multi-agent reinforcement learning involves multiple agents interacting with each other and a shared environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feedback on the quality of actions that they take, thereby affecting learning of policies. In this paper, we propose a method called Shaping Advice in deep Multi-agent reinforcement learning (SAM) to augment the reward signal from the environment with an additional reward termed shaping advice. The shaping advice is given by a difference of potential functions at consecutive time-steps. Each potential function is a function of observations and actions of the agents. The shaping advice needs to be specified only once at the start of training, and can be easily provided by non-experts. We show through theoretical analyses and experimental validation that shaping advice provided by SAM does not distract agents from completing tasks specified by the environment reward. Theoretically, we prove that convergence of policy gradients and value functions when using SAM implies convergence of these quantities in the absence of SAM. Experimentally, we evaluate SAM on three tasks in the multi-agent Particle World environment that have sparse rewards. We observe that using SAM results in agents learning policies to complete tasks faster, and obtain higher rewards than: i) using sparse rewards alone; ii) a state-of-the-art reward redistribution method.


Shaping Advice in Deep Reinforcement Learning

Reinforcement learning involves agents interacting with an environment t...

Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning

This paper considers multi-agent reinforcement learning (MARL) tasks whe...

Curiosity-driven reinforcement learning with homeostatic regulation

We propose a curiosity reward based on information theory principles and...

Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help

Multi-agent reinforcement learning (MARL) has achieved great progress in...

Self Punishment and Reward Backfill for Deep Q-Learning

Reinforcement learning agents learn by encouraging behaviours which maxi...

Reinforcement Learning with Goal-Distance Gradient

Reinforcement learning usually uses the feedback rewards of environmenta...

Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning

Multi-agent reinforcement learning has drawn increasing attention in pra...

Please sign up or login with your details

Forgot password? Click here to reset