Span-Based Optimal Sample Complexity for Average Reward MDPs

• URL: http://arxiv.org/abs/2311.13469v2
• Date: Tue, 19 Mar 2024 18:24:43 GMT
• Title: Span-Based Optimal Sample Complexity for Average Reward MDPs
• Authors: Matthew Zurek, Yudong Chen,
• Abstract summary: We study the sample complexity of learning an $varepsilon$-optimal policy in an average-reward Markov decision process (MDP) under a generative model. We establish the complexity bound $widetildeOleft(SAfracH (1-gamma)2varepsilon2 right)$, where $H$ is the span of the bias function of the optimal policy and $SA$ is the cardinality of the state-action space.
• Score: 6.996002801232415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the sample complexity of learning an $\varepsilon$-optimal policy in an average-reward Markov decision process (MDP) under a generative model. We establish the complexity bound $\widetilde{O}\left(SA\frac{H}{\varepsilon^2} \right)$, where $H$ is the span of the bias function of the optimal policy and $SA$ is the cardinality of the state-action space. Our result is the first that is minimax optimal (up to log factors) in all parameters $S,A,H$ and $\varepsilon$, improving on existing work that either assumes uniformly bounded mixing times for all policies or has suboptimal dependence on the parameters. Our result is based on reducing the average-reward MDP to a discounted MDP. To establish the optimality of this reduction, we develop improved bounds for $\gamma$-discounted MDPs, showing that $\widetilde{O}\left(SA\frac{H}{(1-\gamma)^2\varepsilon^2} \right)$ samples suffice to learn a $\varepsilon$-optimal policy in weakly communicating MDPs under the regime that $\gamma \geq 1 - \frac{1}{H}$, circumventing the well-known lower bound of $\widetilde{\Omega}\left(SA\frac{1}{(1-\gamma)^3\varepsilon^2} \right)$ for general $\gamma$-discounted MDPs. Our analysis develops upper bounds on certain instance-dependent variance parameters in terms of the span parameter. These bounds are tighter than those based on the mixing time or diameter of the MDP and may be of broader use.

Related papers

• Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation [3.2703356989962518]
  We study model-based reinforcement learning with non-linear function approximation. We develop a provably efficient discounted value iteration-based algorithm that works for both infinite-horizon average-reward and discounted-reward settings.
  arXiv  Detail & Related papers  (2024-06-19T15:29:14Z)
• Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs [56.237917407785545]
  We consider the problem of learning an $varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.
  arXiv  Detail & Related papers  (2024-05-10T09:58:47Z)
• Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs [6.996002801232415]
  We study the sample complexity of learning an $varepsilon$-optimal policy in an average-reward Markov decision process (MDP) under a generative model. For weakly communicating MDPs, we establish the complexity bound $widetildeO(SAfracHvarepsilon2 )$, where $H$ is the span of the bias function of the optimal policy and $SA$ is the cardinality of the state-action space.
  arXiv  Detail & Related papers  (2024-03-18T04:52:11Z)
• Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP [58.13930707612128]
  This work considers the sample complexity of obtaining an $varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP) We prove an upper bound of $widetilde O(H varepsilon-3 ln frac1delta)$ samples per state-action pair, where $H := sp(h*)$ is the span of bias of any optimal policy, $varepsilon$ is the accuracy and $delta$ is the failure probability.
  arXiv  Detail & Related papers  (2022-12-01T15:57:58Z)
• 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)
• Best Policy Identification in Linear MDPs [70.57916977441262]
  We investigate the problem of best identification in discounted linear Markov+Delta Decision in the fixed confidence setting under a generative model. The lower bound as the solution of an intricate non- optimization program can be used as the starting point to devise such algorithms.
  arXiv  Detail & Related papers  (2022-08-11T04:12:50Z)
• Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes [91.38793800392108]
  We study reinforcement learning with linear function approximation where the underlying transition probability kernel of the Markov decision process (MDP) is a linear mixture model. We propose a new, computationally efficient algorithm with linear function approximation named $textUCRL-VTR+$ for the aforementioned linear mixture MDPs. To the best of our knowledge, these are the first computationally efficient, nearly minimax optimal algorithms for RL with linear function approximation.
  arXiv  Detail & Related papers  (2020-12-15T18:56:46Z)
• Efficiently Solving MDPs with Stochastic Mirror Descent [38.30919646721354]
  We present a unified framework for approximately solving infinite-horizon Markov decision processes (MDPs) given a linear model. We achieve these results through a more general mirror descent framework for solving bigenerative saddle-point problems with simplex and box domains.
  arXiv  Detail & Related papers  (2020-08-28T17:58:40Z)
• Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity [59.34067736545355]
  Given an MDP with $S$ states, $A$ actions, the discount factor $gamma in (0,1)$, and an approximation threshold $epsilon > 0$, we provide a model-free algorithm to learn an $epsilon$-optimal policy. For small enough $epsilon$, we show an improved algorithm with sample complexity.
  arXiv  Detail & Related papers  (2020-06-06T13:34:41Z)

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.