Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning

Abstract

We present an algorithm, HOMER, for exploration and reinforcement learning in rich observation environments that are summarizable by an unknown latent state space. The algorithm interleaves representation learning to identify a new notion of kinematic state abstraction with strategic exploration to reach new states using the learned abstraction. The algorithm provably explores the environment with sample complexity scaling polynomially in the number of latent states and the time horizon, and, crucially, with no dependence on the size of the observation space, which could be infinitely large. This exploration guarantee further enables sample-efficient global policy optimization for any reward function. On the computational side, we show that the algorithm can be implemented efficiently whenever certain supervised learning problems are tractable. Empirically, we evaluate HOMER on a challenging exploration problem, where we show that the algorithm is exponentially more sample efficient than standard reinforcement learning baselines.

Cited by in corpus (8)

• On Reward-Free Reinforcement Learning with Linear Function Approximation
• Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
• Return-Based Contrastive Representation Learning for Reinforcement Learning
• Structure in Deep Reinforcement Learning: A Survey and Open Problems
• Randomized Value Functions via Posterior State-Abstraction Sampling
• Energy-based Surprise Minimization for Multi-Agent Value Factorization
• Extracting Latent State Representations with Linear Dynamics from Rich Observations
• Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP