Efficient Reinforcement Learning in Probabilistic Reward Machines

• URL: http://arxiv.org/abs/2408.10381v1
• Date: Mon, 19 Aug 2024 19:51:53 GMT
• Title: Efficient Reinforcement Learning in Probabilistic Reward Machines
• Authors: Xiaofeng Lin, Xuezhou Zhang,
• Abstract summary: We design an algorithm for Probabilistic Reward Machines (PRMs) that achieves a regret bound of $widetildeO(sqrtHOAT)$. We also present a new simulation lemma for non-Markovian rewards, which enables reward-free exploration for any non-Markovian reward.
• Score: 15.645062155050732
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we study reinforcement learning in Markov Decision Processes with Probabilistic Reward Machines (PRMs), a form of non-Markovian reward commonly found in robotics tasks. We design an algorithm for PRMs that achieves a regret bound of $\widetilde{O}(\sqrt{HOAT} + H^2O^2A^{3/2} + H\sqrt{T})$, where $H$ is the time horizon, $O$ is the number of observations, $A$ is the number of actions, and $T$ is the number of time-steps. This result improves over the best-known bound, $\widetilde{O}(H\sqrt{OAT})$ of \citet{pmlr-v206-bourel23a} for MDPs with Deterministic Reward Machines (DRMs), a special case of PRMs. When $T \geq H^3O^3A^2$ and $OA \geq H$, our regret bound leads to a regret of $\widetilde{O}(\sqrt{HOAT})$, which matches the established lower bound of $\Omega(\sqrt{HOAT})$ for MDPs with DRMs up to a logarithmic factor. To the best of our knowledge, this is the first efficient algorithm for PRMs. Additionally, we present a new simulation lemma for non-Markovian rewards, which enables reward-free exploration for any non-Markovian reward given access to an approximate planner. Complementing our theoretical findings, we show through extensive experiment evaluations that our algorithm indeed outperforms prior methods in various PRM environments.

Related papers

• Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning [6.236688509180343]
  We study off-dynamics Reinforcement Learning (RL), where the policy training and deployment environments are different. We propose a novel algorithm We-DRIVE-U that enjoys an average suboptimality $widetildemathcalObig(d H cdot min 1/rho, H/sqrtK big)$. We also construct a novel hard instance and derive the first information-theoretic lower bound in this setting.
  arXiv  Detail & Related papers  (2024-09-30T17:21:15Z)
• Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs [72.40181882916089]
  We show that our algorithm achieves an $tildeObig((d+log (|mathcalS|2 |mathcalA|))sqrtKbig)$ regret with full-information feedback, where $d$ is the dimension of a known feature mapping linearly parametrizing the unknown transition kernel of the MDP, $K$ is the number of episodes, $|mathcalS|$ and $|mathcalA|$ are the cardinalities of the state and action spaces
  arXiv  Detail & Related papers  (2023-05-15T05:37:32Z)
• Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR [58.40575099910538]
  We study risk-sensitive Reinforcement Learning (RL), focusing on the objective of Conditional Value at Risk (CVaR) with risk tolerance $tau$. We show the minimax CVaR regret rate is $Omega(sqrttau-1AK)$, where $A$ is the number of actions and $K$ is the number of episodes. We show that our algorithm achieves the optimal regret of $widetilde O(tau-1sqrtSAK)$ under a continuity assumption and in general attains a near
  arXiv  Detail & Related papers  (2023-02-07T02:22:31Z)
• Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning [54.806166861456035]
  We study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. We design a computational efficient algorithm to achieve near-optimal regret of $tildeO(sqrtSAH3Kln (1/delta))$tildeO(cdot) hides logarithmic terms of $(S,A,H,K)$ in $K$ episodes. Our technical contribution are two-fold: 1) a near-optimal design scheme to explore
  arXiv  Detail & Related papers  (2022-10-15T09:22:22Z)
• Reward-Mixing MDPs with a Few Latent Contexts are Learnable [75.17357040707347]
  We consider episodic reinforcement learning in reward-mixing Markov decision processes (RMMDPs) Our goal is to learn a near-optimal policy that nearly maximizes the $H$ time-step cumulative rewards in such a model.
  arXiv  Detail & Related papers  (2022-10-05T22:52:00Z)
• Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs [111.75736569611159]
  We propose the first computationally efficient horizon-free algorithm for linear mixture MDPs. Our algorithm adapts a weighted least square estimator for the unknown transitional dynamic. This also improves upon the best-known algorithms in this setting when $sigma_k2$'s are known.
  arXiv  Detail & Related papers  (2022-05-23T17:59:18Z)
• Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally [58.463668865380946]
  We study the statistical limits of Imitation Learning in episodic Markov Decision Processes (MDPs) with a state space $mathcalS$. We establish an upper bound $O(|mathcalS|H3/2/N)$ for the suboptimality using the Mimic-MD algorithm in Rajaraman et al ( 2020) We show the minimax suboptimality grows as $Omega( H3/2/N)$ when $mathcalS|geq 3$ while the unknown-transition setting suffers from a larger sharp rate
  arXiv  Detail & Related papers  (2021-02-25T15:50:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.