Environment Probing Interaction Policies

TL;DR

This paper introduces the Environment-Probing Interaction (EPI) policy, which actively explores new environments to gather specific information, enabling task policies to adapt and perform better in varied environments, surpassing traditional invariant approaches.

Contribution

The paper proposes a novel environment probing policy that extracts environment-specific information to improve generalization, using a transition predictability reward for training.

Findings

EPI policies outperform standard generalization methods in novel environments.

Environment-specific probing improves task performance.

Transition predictability effectively guides environment understanding.

Abstract

A key challenge in reinforcement learning (RL) is environment generalization: a policy trained to solve a task in one environment often fails to solve the same task in a slightly different test environment. A common approach to improve inter-environment transfer is to learn policies that are invariant to the distribution of testing environments. However, we argue that instead of being invariant, the policy should identify the specific nuances of an environment and exploit them to achieve better performance. In this work, we propose the 'Environment-Probing' Interaction (EPI) policy, a policy that probes a new environment to extract an implicit understanding of that environment's behavior. Once this environment-specific information is obtained, it is used as an additional input to a task-specific policy that can now perform environment-conditioned actions to solve a task. To learn these EPI-policies, we present a reward function based on transition predictability. Specifically, a higher reward is given if the trajectory generated by the EPI-policy can be used to better predict transitions. We experimentally show that EPI-conditioned task-specific policies significantly outperform commonly used policy generalization methods on novel testing environments.