Improved Sample Complexity for Incremental Autonomous Exploration in MDPs

Conference on Neural Information Processing Systems (NeurIPS)


We investigate the exploration of an unknown environment when no reward function is provided. Building on the incremental exploration setting introduced by Lim and Auer [1], we define the objective of learning the set of ε-optimal goal-conditioned policies attaining all states that are incrementally reachable within L steps (in expectation) from a reference state s0. In this paper, we introduce a novel model-based approach that interleaves discovering new states from s0 and improving the accuracy of a model estimate that is used to compute goal-conditioned policies to reach newly discovered states. The resulting algorithm, DisCo, achieves a sample complexity scaling as Õ(L5SL + ε ΓL + ε A ε-2), where A is the number of actions, SL + ε is the number of states that are incrementally reachable from s0 in L + ε steps, and ΓL + ε  is the branching factor of the dynamics over such states. This improves over the algorithm proposed in [1] in both ε and L at the cost of an extra ΓL+ ε factor, which is small in most environments of interest. Furthermore, DisCo is the first algorithm that can return an  ε/cmin-optimal policy for any cost-sensitive shortest-path problem defined on the L-reachable states with minimum cost cmin. Finally, we report preliminary empirical results confirming our theoretical findings.

Related Publications

All Publications

Uncertainty and Robustness in Deep Learning Workshop at ICML - June 24, 2021

DAIR: Data Augmented Invariant Regularization

Tianjian Huang, Chinnadhurai Sankar, Pooyan Amini, Satwik Kottur, Alborz Geramifard, Meisam Razaviyayn, Ahmad Beirami

AutoML Workshop at NeurIPS - July 18, 2021

Neural Fixed-Point Acceleration for Convex Optimization

Shobha Venkataraman, Brandon Amos

Federated Learning for User Privacy and Data Confidentiality Workshop At ICML - July 24, 2021

Federated Learning with Buffered Asynchronous Aggregation

John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Malek, Dzmitry Huba

UAI - July 28, 2021

A Nonmyopic Approach to Cost-Constrained Bayesian Optimization

Eric Hans Lee, David Eriksson, Valerio Perrone, Matthias Seeger

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy