CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations

TL;DR

This paper introduces CEIP, a novel reinforcement learning method that combines multiple implicit priors with explicit retrieval mechanisms to improve learning efficiency in sparse reward environments.

Contribution

CEIP innovatively integrates multiple implicit priors via normalizing flows with explicit retrieval, enhancing reinforcement learning with demonstrations.

Findings

CEIP outperforms state-of-the-art methods in three challenging environments.

Combining explicit and implicit priors improves learning efficiency.

Using multiple implicit priors provides a more complex and effective prior representation.

Abstract

Although reinforcement learning has found widespread use in dense reward settings, training autonomous agents with sparse rewards remains challenging. To address this difficulty, prior work has shown promising results when using not only task-specific demonstrations but also task-agnostic albeit somewhat related demonstrations. In most cases, the available demonstrations are distilled into an implicit prior, commonly represented via a single deep net. Explicit priors in the form of a database that can be queried have also been shown to lead to encouraging results. To better benefit from available demonstrations, we develop a method to Combine Explicit and Implicit Priors (CEIP). CEIP exploits multiple implicit priors in the form of normalizing flows in parallel to form a single complex prior. Moreover, CEIP uses an effective explicit retrieval and push-forward mechanism to condition the implicit priors. In three challenging environments, we find the proposed CEIP method to improve upon sophisticated state-of-the-art techniques.