Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model

• URL: http://arxiv.org/abs/2604.16111v1
• Date: Fri, 17 Apr 2026 14:47:52 GMT
• Title: Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model
• Abstract summary: We study the sample complexity of learning an $$-optimal policy in the Shortest Path (SSP) problem.<n>We show that there exists a worst-case SSP instance with $S$ states, $A$ actions, minimum cost $c_min$, and maximum expected cost of the optimal policy over all states $B_star$.<n>Surprisingly, this implies that whenever $c_min = 0$ an SSP problem may not be learnable.
• Score: 67.75889920324124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the sample complexity of learning an $ε$-optimal policy in the Stochastic Shortest Path (SSP) problem. We first derive sample complexity bounds when the learner has access to a generative model. We show that there exists a worst-case SSP instance with $S$ states, $A$ actions, minimum cost $c_{\min}$, and maximum expected cost of the optimal policy over all states $B_{\star}$, where any algorithm requires at least $Ω(SAB_{\star}^3/(c_{\min}ε^2))$ samples to return an $ε$-optimal policy with high probability. Surprisingly, this implies that whenever $c_{\min} = 0$ an SSP problem may not be learnable, thus revealing that learning in SSPs is strictly harder than in the finite-horizon and discounted settings. We complement this lower bound with an algorithm that matches it, up to logarithmic factors, in the general case, and an algorithm that matches it up to logarithmic factors even when $c_{\min} = 0$, but only under the condition that the optimal policy has a bounded hitting time to the goal state.

Related papers

• Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning [0.0]
  We prove a novel result on the convergence rate of the policy algorithm. We show that the algorithm returns an optimal policy after $tildeO(SAK3log3frac1delta)$ sampled episodes.
  arXiv  Detail & Related papers  (2024-10-03T21:11:29Z)
• Finding good policies in average-reward Markov Decision Processes without prior knowledge [19.89784209009327]
  We revisit the identification of an $varepsilon$-optimal policy in average-reward Decision (MDP) By relying on a diameter estimation procedure, we propose the first algorithm for $(varepsilon,delta)$-PAC-PAC policy identification.
  arXiv  Detail & Related papers  (2024-05-27T12:24:14Z)
• Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path [80.60592344361073]
  We study the Shortest Path (SSP) problem with a linear mixture transition kernel. An agent repeatedly interacts with a environment and seeks to reach certain goal state while minimizing the cumulative cost. Existing works often assume a strictly positive lower bound of the iteration cost function or an upper bound of the expected length for the optimal policy.
  arXiv  Detail & Related papers  (2024-02-14T07:52:00Z)
• Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise [50.64137465792738]
  We show that any efficient SQ algorithm for the problem requires sample complexity at least $Omega(d1/2/(maxp, epsilon)2)$. Our lower bound suggests that this quadratic dependence on $1/epsilon$ is inherent for efficient algorithms.
  arXiv  Detail & Related papers  (2023-07-13T18:59:28Z)
• Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path [106.37656068276902]
  We study the sample complexity of learning an $epsilon$-optimal policy in the Shortest Path (SSP) problem. We derive complexity bounds when the learner has access to a generative model. We show that there exists a worst-case SSP instance with $S$ states, $A$ actions, minimum cost $c_min$, and maximum expected cost of the optimal policy over all states $B_star$.
  arXiv  Detail & Related papers  (2022-10-10T18:34:32Z)
• 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)
• Overcoming the Long Horizon Barrier for Sample-Efficient Reinforcement Learning with Latent Low-Rank Structure [9.759209713196718]
  We consider a class of MDPs for which the associated optimal $Q*$ function is low rank, where the latent features are unknown. We show that under stronger low rank structural assumptions, given access to a generative model, Low Rank Monte Carlo Policy Iteration (LR-MCPI) and Low Rank Empirical Value Iteration (LR-EVI) achieve the desired sample complexity of $tildeOleft((|S|+|A|)mathrmpoly(d,H)/epsilon2right)$ for a rank
  arXiv  Detail & Related papers  (2022-06-07T20:39:51Z)
• The Curse of Passive Data Collection in Batch Reinforcement Learning [82.6026077420886]
  In high stake applications, active experimentation may be considered too risky and thus data are often collected passively. While in simple cases, such as in bandits, passive and active data collection are similarly effective, the price of passive sampling can be much higher when collecting data from a system with controlled states.
  arXiv  Detail & Related papers  (2021-06-18T07:54:23Z)
• 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.