Solving Long-run Average Reward Robust MDPs via Stochastic Games

• URL: http://arxiv.org/abs/2312.13912v2
• Date: Tue, 30 Apr 2024 17:05:38 GMT
• Title: Solving Long-run Average Reward Robust MDPs via Stochastic Games
• Authors: Krishnendu Chatterjee, Ehsan Kafshdar Goharshady, Mehrdad Karrabi, Petr Novotný, Đorđe Žikelić,
• Abstract summary: Robust Markov decision processes (RMDPs) assign to each transition an uncertainty set rather than a single probability value. We show that it can be reduced to solving long-run average reward turn-based games with finite state and action spaces. We present Robust Polytopic Policy Iteration (RPPI), a novel policy iteration algorithm for solving long-run average reward polytopic RMDPs.
• Score: 6.183091173390457
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Markov decision processes (MDPs) provide a standard framework for sequential decision making under uncertainty. However, MDPs do not take uncertainty in transition probabilities into account. Robust Markov decision processes (RMDPs) address this shortcoming of MDPs by assigning to each transition an uncertainty set rather than a single probability value. In this work, we consider polytopic RMDPs in which all uncertainty sets are polytopes and study the problem of solving long-run average reward polytopic RMDPs. We present a novel perspective on this problem and show that it can be reduced to solving long-run average reward turn-based stochastic games with finite state and action spaces. This reduction allows us to derive several important consequences that were hitherto not known to hold for polytopic RMDPs. First, we derive new computational complexity bounds for solving long-run average reward polytopic RMDPs, showing for the first time that the threshold decision problem for them is in $NP \cap coNP$ and that they admit a randomized algorithm with sub-exponential expected runtime. Second, we present Robust Polytopic Policy Iteration (RPPI), a novel policy iteration algorithm for solving long-run average reward polytopic RMDPs. Our experimental evaluation shows that RPPI is much more efficient in solving long-run average reward polytopic RMDPs compared to state-of-the-art methods based on value iteration.

Related papers

• RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation [73.2390735383842]
  We introduce the first sample-efficient algorithm for LMDPs without any additional structural assumptions. We show how these can be used to derive near-optimal guarantees of an optimistic exploration algorithm. These results can be valuable for a wide range of interactive learning problems beyond LMDPs, and especially, for partially observed environments.
  arXiv  Detail & Related papers  (2024-06-03T14:51:27Z)
• On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes [50.68789924454235]
  We present the first finite time global convergence analysis of policy gradient in the context of average reward Markov decision processes (MDPs) Our analysis shows that the policy gradient iterates converge to the optimal policy at a sublinear rate of $Oleft(frac1Tright),$ which translates to $Oleft(log(T)right)$ regret, where $T$ represents the number of iterations.
  arXiv  Detail & Related papers  (2024-03-11T15:25:03Z)
• The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model [61.87673435273466]
  This paper investigates model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision processes (RMDPs), aimed at learning a policy that optimize the worst-case performance when the deployed environment falls within a prescribed uncertainty set around the nominal MDP.
  arXiv  Detail & Related papers  (2023-05-26T02:32:03Z)
• Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization [64.60253456266872]
  Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. Regularized MDPs show more stability in policy learning without impairing time complexity. Bellman operators enable us to derive planning and learning schemes with convergence and generalization guarantees.
  arXiv  Detail & Related papers  (2023-03-12T13:03:28Z)
• Policy Gradient in Robust MDPs with Global Convergence Guarantee [13.40471012593073]
  Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. This paper proposes a new Double-Loop Robust Policy Gradient (DRPG), the first generic policy gradient method for RMDPs. In contrast with prior robust policy gradient algorithms, DRPG monotonically reduces approximation errors to guarantee convergence to a globally optimal policy.
  arXiv  Detail & Related papers  (2022-12-20T17:14:14Z)
• First-order Policy Optimization for Robust Markov Decision Process [40.2022466644885]
  We consider the problem of solving robust Markov decision process (MDP) MDP involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. For $(mathbfs,mathbfa)$-rectangular uncertainty sets, we establish several structural observations on the robust objective.
  arXiv  Detail & Related papers  (2022-09-21T18:10:28Z)
• Stochastic first-order methods for average-reward Markov decision processes [10.023632561462712]
  We study average-reward Markov decision processes (AMDPs) and develop novel first-order methods with strong theoretical guarantees for both policy optimization and policy evaluation. By combining the policy evaluation and policy optimization parts, we establish sample complexity results for solving AMDPs under both generative and Markovian noise models.
  arXiv  Detail & Related papers  (2022-05-11T23:02:46Z)
• Under-Approximating Expected Total Rewards in POMDPs [68.8204255655161]
  We consider the optimal expected total reward to reach a goal state in a partially observable Markov decision process (POMDP) We use mixed-integer linear programming (MILP) to find such minimal probability shifts and experimentally show that our techniques scale quite well.
  arXiv  Detail & Related papers  (2022-01-21T16:43:03Z)
• Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits [8.136957953239254]
  We study a finite-horizon restless multi-armed bandit problem with multiple actions dubbed R(MA)2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both the current state of the corresponding MDP and the action taken. Since finding the optimal policy is typically intractable, we propose a computationally appealing index policy which we call Occupancy-Measured-Reward Index Policy.
  arXiv  Detail & Related papers  (2021-09-20T21:40:12Z)
• Safe Exploration by Solving Early Terminated MDP [77.10563395197045]
  We introduce a new approach to address safe RL problems under the framework of Early TerminatedP (ET-MDP) We first define the ET-MDP as an unconstrained algorithm with the same optimal value function as its corresponding CMDP. An off-policy algorithm based on context models is then proposed to solve the ET-MDP, which thereby solves the corresponding CMDP with better performance and improved learning efficiency.
  arXiv  Detail & Related papers  (2021-07-09T04:24:40Z)
• Model-Free Algorithm and Regret Analysis for MDPs with Long-Term Constraints [38.2783003051101]
  This paper uses concepts from constrained optimization and Q-learning to propose an algorithm for CMDP with long-term constraints. We note that these are the first results on regret analysis for MDP with long-term constraints, where the transition probabilities are not known apriori.
  arXiv  Detail & Related papers  (2020-06-10T17:19:29Z)

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.