Finding good policies in average-reward Markov Decision Processes without prior knowledge
- URL: http://arxiv.org/abs/2405.17108v1
- Date: Mon, 27 May 2024 12:24:14 GMT
- Title: Finding good policies in average-reward Markov Decision Processes without prior knowledge
- Authors: Adrienne Tuynman, Rémy Degenne, Emilie Kaufmann,
- Abstract summary: 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.
- Score: 19.89784209009327
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We revisit the identification of an $\varepsilon$-optimal policy in average-reward Markov Decision Processes (MDP). In such MDPs, two measures of complexity have appeared in the literature: the diameter, $D$, and the optimal bias span, $H$, which satisfy $H\leq D$. Prior work have studied the complexity of $\varepsilon$-optimal policy identification only when a generative model is available. In this case, it is known that there exists an MDP with $D \simeq H$ for which the sample complexity to output an $\varepsilon$-optimal policy is $\Omega(SAD/\varepsilon^2)$ where $S$ and $A$ are the sizes of the state and action spaces. Recently, an algorithm with a sample complexity of order $SAH/\varepsilon^2$ has been proposed, but it requires the knowledge of $H$. We first show that the sample complexity required to estimate $H$ is not bounded by any function of $S,A$ and $H$, ruling out the possibility to easily make the previous algorithm agnostic to $H$. By relying instead on a diameter estimation procedure, we propose the first algorithm for $(\varepsilon,\delta)$-PAC policy identification that does not need any form of prior knowledge on the MDP. Its sample complexity scales in $SAD/\varepsilon^2$ in the regime of small $\varepsilon$, which is near-optimal. In the online setting, our first contribution is a lower bound which implies that a sample complexity polynomial in $H$ cannot be achieved in this setting. Then, we propose an online algorithm with a sample complexity in $SAD^2/\varepsilon^2$, as well as a novel approach based on a data-dependent stopping rule that we believe is promising to further reduce this bound.
Related papers
- 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) - 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) - 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) - Improved Sample Complexity for Incremental Autonomous Exploration in
MDPs [132.88757893161699]
We learn the set of $epsilon$-optimal goal-conditioned policies attaining all states that are incrementally reachable within $L$ steps.
DisCo is the first algorithm that can return an $epsilon/c_min$-optimal policy for any cost-sensitive shortest-path problem.
arXiv Detail & Related papers (2020-12-29T14:06:09Z) - 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.