English
Related papers

Related papers: Optimism in Reinforcement Learning with Generalize…

200 papers

We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value…

Machine Learning · Computer Science 2020-06-30 Andrea Zanette , Alessandro Lazaric , Mykel Kochenderfer , Emma Brunskill

We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting. We then apply it to study finite-time horizon stochastic control problems with linear dynamics but unknown coefficients and…

Machine Learning · Computer Science 2021-12-22 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

We propose an algorithm for tabular episodic reinforcement learning with constraints. We provide a modular analysis with strong theoretical guarantees for settings with concave rewards and convex constraints, and for settings with hard…

Off-policy deep reinforcement learning algorithms commonly compensate for overestimation bias during temporal-difference learning by utilizing pessimistic estimates of the expected target returns. In this work, we propose Generalized…

Machine Learning · Computer Science 2023-03-07 Edoardo Cetin , Oya Celiktutan

We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves…

Machine Learning · Computer Science 2019-12-12 Aristide Tossou , Debabrota Basu , Christos Dimitrakakis

In this paper, we study the problem of regret minimization for episodic Reinforcement Learning (RL) both in the model-free and the model-based setting. We focus on learning with general function classes and general model classes, and we…

Machine Learning · Computer Science 2022-03-04 Grigoris Velegkas , Zhuoran Yang , Amin Karbasi

We derive an alternative proof for the regret of Thompson sampling (\ts) in the stochastic linear bandit setting. While we obtain a regret bound of order $\widetilde{O}(d^{3/2}\sqrt{T})$ as in previous results, the proof sheds new light on…

Machine Learning · Statistics 2019-11-06 Marc Abeille , Alessandro Lazaric

We study the reinforcement learning (RL) problem in a constrained Markov decision process (CMDP), where an agent explores the environment to maximize the expected cumulative reward while satisfying a single constraint on the expected total…

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimization perspective, without addressing the problem of…

Machine Learning · Computer Science 2020-06-19 Yonathan Efroni , Lior Shani , Aviv Rosenberg , Shie Mannor

We consider an adversarial variant of the classic $K$-armed linear contextual bandit problem where the sequence of loss functions associated with each arm are allowed to change without restriction over time. Under the assumption that the…

Machine Learning · Computer Science 2022-05-25 Gergely Neu , Julia Olkhovskaya

While policy-based reinforcement learning (RL) achieves tremendous successes in practice, it is significantly less understood in theory, especially compared with value-based RL. In particular, it remains elusive how to design a provably…

Machine Learning · Computer Science 2024-04-02 Qi Cai , Zhuoran Yang , Chi Jin , Zhaoran Wang

We study multi-agent reinforcement learning in the setting of episodic Markov decision processes, where multiple agents cooperate via communication through a central server. We propose a provably efficient algorithm based on value iteration…

Machine Learning · Computer Science 2023-06-27 Yifei Min , Jiafan He , Tianhao Wang , Quanquan Gu

Strong worst-case performance bounds for episodic reinforcement learning exist but fortunately in practice RL algorithms perform much better than such bounds would predict. Algorithms and theory that provide strong problem-dependent bounds…

Machine Learning · Computer Science 2019-11-05 Andrea Zanette , Emma Brunskill

This paper studies the adaptive optimal stationary control of continuous-time linear stochastic systems with both additive and multiplicative noises, using reinforcement learning techniques. Based on policy iteration, a novel off-policy…

Systems and Control · Electrical Eng. & Systems 2021-12-07 Bo Pang , Zhong-Ping Jiang

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the…

Machine Learning · Computer Science 2021-10-27 Christoph Dann , Teodor V. Marinov , Mehryar Mohri , Julian Zimmert

We establish that an optimistic variant of Q-learning applied to a fixed-horizon episodic Markov decision process with an aggregated state representation incurs regret $\tilde{\mathcal{O}}(\sqrt{H^5 M K} + \epsilon HK)$, where $H$ is the…

Machine Learning · Statistics 2020-02-20 Shi Dong , Benjamin Van Roy , Zhengyuan Zhou

We propose an optimistic model-based algorithm, dubbed SMRL, for finite-horizon episodic reinforcement learning (RL) when the transition model is specified by exponential family distributions with $d$ parameters and the reward is bounded…

Machine Learning · Computer Science 2023-01-10 Gene Li , Junbo Li , Anmol Kabra , Nathan Srebro , Zhaoran Wang , Zhuoran Yang

We give a simple optimistic algorithm for which it is easy to derive regret bounds of $\tilde{O}(\sqrt{t_{\rm mix} SAT})$ after $T$ steps in uniformly ergodic Markov decision processes with $S$ states, $A$ actions, and mixing time parameter…

Machine Learning · Computer Science 2019-01-23 Ronald Ortner

We study the adaptive control of an unknown linear system with a quadratic cost function subject to safety constraints on both the states and actions. The challenges of this problem arise from the tension among safety, exploration,…

Systems and Control · Electrical Eng. & Systems 2021-11-02 Yingying Li , Subhro Das , Jeff Shamma , Na Li

This paper presents the first non-asymptotic result showing that a model-free algorithm can achieve a logarithmic cumulative regret for episodic tabular reinforcement learning if there exists a strictly positive sub-optimality gap in the…

Machine Learning · Computer Science 2021-02-24 Kunhe Yang , Lin F. Yang , Simon S. Du