Denoised MDPs: Learning World Models Better Than the World Itself

TL;DR

This paper introduces Denoised MDPs, a framework for learning cleaner, more abstract world models in reinforcement learning by explicitly removing noise distractors, leading to improved performance across various tasks.

Contribution

The paper proposes a novel approach to factor out noise in reinforcement learning by learning Denoised MDPs, enhancing model quality and task performance.

Findings

Denoised MDPs outperform raw observation models in control tasks.

The approach improves joint position regression accuracy.

Experiments demonstrate robustness across multiple RL environments.

Abstract

The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence. With this ability, humans can efficiently perform real world tasks without considering all possible nuisance factors.How can artificial agents do the same? What kind of information can agents safely discard as noises? In this work, we categorize information out in the wild into four types based on controllability and relation with reward, and formulate useful information as that which is both controllable and reward-relevant. This framework clarifies the kinds information removed by various prior work on representation learning in reinforcement learning (RL), and leads to our proposed approach of learning a Denoised MDP that explicitly factors out certain noise distractors. Extensive experiments on variants of DeepMind Control Suite and RoboDesk demonstrate superior performance of our denoised world model over using raw observations alone, and over prior works, across policy optimization control tasks as well as the non-control task of joint position regression.