Pessimistic Model-based Offline RL: PAC Bounds and Posterior Sampling under Partial Coverage

by   Masatoshi Uehara, et al.

We study model-based offline Reinforcement Learning with general function approximation. We present an algorithm named Constrained Pessimistic Policy Optimization (CPPO) which leverages a general function class and uses a constraint to encode pessimism. Under the assumption that the ground truth model belongs to our function class, CPPO can learn with the offline data only providing partial coverage, i.e., it can learn a policy that completes against any policy that is covered by the offline data, in polynomial sample complexity with respect to the statistical complexity of the function class. We then demonstrate that this algorithmic framework can be applied to many specialized Markov Decision Processes where the additional structural assumptions can further refine the concept of partial coverage. One notable example is low-rank MDP with representation learning where the partial coverage is defined using the concept of relative condition number measured by the underlying unknown ground truth feature representation. Finally, we introduce and study the Bayesian setting in offline RL. The key benefit of Bayesian offline RL is that algorithmically, we do not need to explicitly construct pessimism or reward penalty which could be hard beyond models with linear structures. We present a posterior sampling-based incremental policy optimization algorithm (PS-PO) which proceeds by iteratively sampling a model from the posterior distribution and performing one-step incremental policy optimization inside the sampled model. Theoretically, in expectation with respect to the prior distribution, PS-PO can learn a near optimal policy under partial coverage with polynomial sample complexity.


page 1

page 2

page 3

page 4


Representation Learning for Online and Offline RL in Low-rank MDPs

This work studies the question of Representation Learning in RL: how can...

On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples

Offline reinforcement learning (offline RL) considers problems where lea...

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

Offline or batch reinforcement learning seeks to learn a near-optimal po...

Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instruments

We study offline reinforcement learning under a novel model called strat...

Matrix Estimation for Offline Reinforcement Learning with Low-Rank Structure

We consider offline Reinforcement Learning (RL), where the agent does no...

Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation

Offline reinforcement learning (RL) concerns pursuing an optimal policy ...

Refined Value-Based Offline RL under Realizability and Partial Coverage

In offline reinforcement learning (RL) we have no opportunity to explore...

Please sign up or login with your details

Forgot password? Click here to reset