Temporal Predictive Coding For Model-Based Planning In Latent Space

TL;DR

This paper introduces a temporal predictive coding approach for model-based planning in latent space, effectively filtering task-relevant information from complex, high-dimensional observations using an information-theoretic method.

Contribution

It proposes a novel temporal predictive coding method combined with a recurrent state space model to improve planning in high-dimensional, complex environments.

Findings

Outperforms existing methods in complex-background DMControl tasks

Maintains competitive performance in standard environments

Effectively encodes task-relevant information while ignoring irrelevant background

Abstract

High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments. To handle high-dimensional sensory inputs, existing approaches use representation learning to map high-dimensional observations into a lower-dimensional latent space that is more amenable to dynamics estimation and planning. In this work, we present an information-theoretic approach that employs temporal predictive coding to encode elements in the environment that can be predicted across time. Since this approach focuses on encoding temporally-predictable information, we implicitly prioritize the encoding of task-relevant components over nuisance information within the environment that are provably task-irrelevant. By learning this representation in conjunction with a recurrent state space model, we can then perform planning in latent space. We evaluate our model on a challenging modification of standard DMControl tasks where the background is replaced with natural videos that contain complex but irrelevant information to the planning task. Our experiments show that our model is superior to existing methods in the challenging complex-background setting while remaining competitive with current state-of-the-art models in the standard setting.