Shaping Advice in Deep Reinforcement Learning

TL;DR

This paper introduces a method to augment reinforcement learning with shaping advice, using potential functions to improve learning efficiency and performance in sparse reward environments, with theoretical guarantees and practical algorithms for single and multi-agent settings.

Contribution

The paper proposes a novel approach to reward shaping in reinforcement learning using potential functions, providing theoretical analysis, algorithms, and empirical validation for both single and multi-agent systems.

Findings

Shaping advice accelerates policy learning in sparse reward tasks.

Agents with shaping advice achieve higher rewards faster.

Theoretical convergence guarantees are established for the proposed methods.

Abstract

Reinforcement learning involves agents interacting with an 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 to methods to augment the reward signal from the environment with an additional reward termed shaping advice in both single and multi-agent reinforcement learning. The shaping advice is specified as a difference of potential functions at consecutive time-steps. Each potential function is a function of observations and actions of the agents. The use of potential functions is underpinned by an insight that the total potential when starting from any state and returning to the same state is always equal to zero. We show through theoretical analyses and experimental validation that the shaping advice does not distract agents from completing tasks specified by the environment reward. Theoretically, we prove that the convergence of policy gradients and value functions when using shaping advice implies the convergence of these quantities in the absence of shaping advice. We design two algorithms- Shaping Advice in Single-agent reinforcement learning (SAS) and Shaping Advice in Multi-agent reinforcement learning (SAM). Shaping advice in SAS and SAM needs to be specified only once at the start of training, and can easily be provided by non-experts. Experimentally, we evaluate SAS and SAM on two tasks in single-agent environments and three tasks in multi-agent environments that have sparse rewards. We observe that using shaping advice results in agents learning policies to complete tasks faster, and obtain higher rewards than algorithms that do not use shaping advice.