Provably Efficient Offline Reinforcement Learning in Regular Decision Processes
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Forlagets udgivne version, 645 KB, PDF-dokument
This paper deals with offline (or batch) Reinforcement Learning (RL) in episodic Regular Decision Processes (RDPs). RDPs are the subclass of Non-Markov Decision Processes where the dependency on the history of past events can be captured by a finite-state automaton. We consider a setting where the automaton that underlies the RDP is unknown, and a learner strives to learn a near-optimal policy using pre-collected data, in the form of non-Markov sequences of observations, without further exploration. We present RegORL, an algorithm that suitably combines automata learning techniques and state-of-the-art algorithms for offline RL in MDPs. RegORL has a modular design allowing one to use any off-the-shelf offline RL algorithm in MDPs. We report a non-asymptotic high-probability sample complexity bound for RegORL to yield an ε-optimal policy, which makes appear a notion of concentrability relevant for RDPs. Furthermore, we present a sample complexity lower bound for offline RL in RDPs. To our best knowledge, this is the first work presenting a provably efficient algorithm for offline learning in RDPs.
Originalsprog | Engelsk |
---|---|
Titel | Advances in Neural Information Processing Systems 36 (NeurIPS 2023) |
Antal sider | 34 |
Forlag | NeurIPS Proceedings |
Publikationsdato | 2023 |
Status | Udgivet - 2023 |
Begivenhed | 37th Conference on Neural Information Processing Systems - NeurIPS 2023 - New Orleans., USA Varighed: 10 dec. 2023 → 16 dec. 2023 |
Konference
Konference | 37th Conference on Neural Information Processing Systems - NeurIPS 2023 |
---|---|
Land | USA |
By | New Orleans. |
Periode | 10/12/2023 → 16/12/2023 |
Navn | Advances in Neural Information Processing Systems |
---|---|
Vol/bind | 36 |
ISSN | 1049-5258 |
Links
ID: 386160160