Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption

TL;DR

This paper introduces MACURA, a model-based reinforcement learning algorithm that adaptively determines where to trust the model using uncertainty estimates, leading to improved data efficiency and performance.

Contribution

It proposes an uncertainty-aware rollout adaptation mechanism for model-based RL, addressing the challenge of local model accuracy in dynamic environments.

Findings

Substantial improvements in data efficiency on MuJoCo benchmarks

Better performance compared to state-of-the-art deep MBRL methods

Effective uncertainty-based rollout length adaptation

Abstract

Dyna-style model-based reinforcement learning (MBRL) combines model-free agents with predictive transition models through model-based rollouts. This combination raises a critical question: 'When to trust your model?'; i.e., which rollout length results in the model providing useful data? Janner et al. (2019) address this question by gradually increasing rollout lengths throughout the training. While theoretically tempting, uniform model accuracy is a fallacy that collapses at the latest when extrapolating. Instead, we propose asking the question 'Where to trust your model?'. Using inherent model uncertainty to consider local accuracy, we obtain the Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption (MACURA) algorithm. We propose an easy-to-tune rollout mechanism and demonstrate substantial improvements in data efficiency and performance compared to state-of-the-art deep MBRL methods on the MuJoCo benchmark.