Off-Policy Adversarial Inverse Reinforcement Learning

Samin Yeasar Arnob

Student First Author: Yes

Keywords: Reinforcement learning, Transfer learning, Inverse reinforcement learning

Previously Published: arxiv.org

Abstract: Adversarial Imitation Learning (AIL) is a class of algorithms in Reinforcement learning (RL), which tries to imitate an expert without taking any reward from the environment and does not provide expert behavior directly to the policy training. Rather, an agent learns a policy distribution that minimizes the difference from expert behavior in adversarial setting. Adversarial Inverse Reinforcement Learning (AIRL) leverages the idea of AIL, integrates a reward function approximation along with learning the policy and shows the utility of IRL in the transfer learning setting. But the reward function approximator that enables transfer learning does not perform well in imitation tasks. We propose an Off-Policy Adversarial Inverse Reinforcement Learning (Off-policy-AIRL) algorithm which is sample efficient as well as gives good imitation performance compared to the state-of-the-art AIL algorithm in the continuous control tasks. For the same reward function approximator, we show the utility of learning our algorithm over AIL by using the learned reward function to retrain the policy over a task under significant variation where expert demonstrations are absent.

TL;DR: Proposes inverse reinforcement learning that allows improve imitation performance as well as transfer learned knowlwdge over new task under certain dynamic changes.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2005.01138/code)