Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning

TL;DR

This paper introduces a meta-gradient algorithm that adaptively tunes state-query probabilities in Dyna-style planning, enhancing sample efficiency and robustness in model-based reinforcement learning, especially under resource constraints and changing environments.

Contribution

The paper presents a novel online meta-gradient method for adaptive sampling in Dyna planning, improving efficiency and avoiding common pitfalls of traditional sampling strategies.

Findings

Meta-gradient method outperforms conventional sampling strategies.

Improves sample efficiency of the overall RL process.

Reduces issues like sampling inaccurate transitions and credit assignment stalls.

Abstract

We study how a Reinforcement Learning (RL) system can remain sample-efficient when learning from an imperfect model of the environment. This is particularly challenging when the learning system is resource-constrained and in continual settings, where the environment dynamics change. To address these challenges, our paper introduces an online, meta-gradient algorithm that tunes a probability with which states are queried during Dyna-style planning. Our study compares the aggregate, empirical performance of this meta-gradient method to baselines that employ conventional sampling strategies. Results indicate that our method improves efficiency of the planning process, which, as a consequence, improves the sample-efficiency of the overall learning process. On the whole, we observe that our meta-learned solutions avoid several pathologies of conventional planning approaches, such as sampling inaccurate transitions and those that stall credit assignment. We believe these findings could prove useful, in future work, for designing model-based RL systems at scale.