Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Models

TL;DR

This paper introduces a reward shaping method for reinforcement learning that leverages generative models trained on imperfect demonstrations to improve learning efficiency and robustness in robotic tasks.

Contribution

It proposes a novel approach that uses generative models for reward shaping from suboptimal demonstrations, enhancing data efficiency and robustness in reinforcement learning.

Findings

Accelerates policy learning by focusing exploration on high-value regions.

Effective with suboptimal and noisy demonstration data.

Validated through extensive simulations and real robot experiments.

Abstract

The potential benefits of model-free reinforcement learning to real robotics systems are limited by its uninformed exploration that leads to slow convergence, lack of data-efficiency, and unnecessary interactions with the environment. To address these drawbacks we propose a method that combines reinforcement and imitation learning by shaping the reward function with a state-and-action-dependent potential that is trained from demonstration data, using a generative model. We show that this accelerates policy learning by specifying high-value areas of the state and action space that are worth exploring first. Unlike the majority of existing methods that assume optimal demonstrations and incorporate the demonstration data as hard constraints on policy optimization, we instead incorporate demonstration data as advice in the form of a reward shaping potential trained as a generative model of states and actions. In particular, we examine both normalizing flows and Generative Adversarial Networks to represent these potentials. We show that, unlike many existing approaches that incorporate demonstrations as hard constraints, our approach is unbiased even in the case of suboptimal and noisy demonstrations. We present an extensive range of simulations, as well as experiments on the Franka Emika 7DOF arm, to demonstrate the practicality of our method.