Anytime-Constrained Reinforcement Learning

• URL: http://arxiv.org/abs/2311.05511v3
• Date: Thu, 13 Jun 2024 07:10:30 GMT
• Title: Anytime-Constrained Reinforcement Learning
• Authors: Jeremy McMahan, Xiaojin Zhu,
• Abstract summary: We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. We show that there exist optimal deterministic policies augmented with cumulative costs. We show that computing non-trivial approximately optimal policies is NP-hard in general.
• Score: 6.981971551979697
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no longer sufficient, we show that there exist optimal deterministic policies augmented with cumulative costs. In fact, we present a fixed-parameter tractable reduction from anytime-constrained cMDPs to unconstrained MDPs. Our reduction yields planning and learning algorithms that are time and sample-efficient for tabular cMDPs so long as the precision of the costs is logarithmic in the size of the cMDP. However, we also show that computing non-trivial approximately optimal policies is NP-hard in general. To circumvent this bottleneck, we design provable approximation algorithms that efficiently compute or learn an arbitrarily accurate approximately feasible policy with optimal value so long as the maximum supported cost is bounded by a polynomial in the cMDP or the absolute budget. Given our hardness results, our approximation guarantees are the best possible under worst-case analysis.

Related papers

• Near-Optimal Learning and Planning in Separated Latent MDPs [70.88315649628251]
  We study computational and statistical aspects of learning Latent Markov Decision Processes (LMDPs) In this model, the learner interacts with an MDP drawn at the beginning of each epoch from an unknown mixture of MDPs.
  arXiv  Detail & Related papers  (2024-06-12T06:41:47Z)
• Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets [10.26382228865201]
  We propose policy gradient algorithms for robust infinite-horizon Markov decision processes (MDPs) with non-rectangular uncertainty sets. The corresponding robust MDPs cannot be solved with dynamic programming techniques and are in fact provably intractable. We thus present the first complete solution scheme for robust MDPs with non-rectangular uncertainty sets offering global optimality guarantees.
  arXiv  Detail & Related papers  (2023-05-30T13:02:25Z)
• An Efficient Solution to s-Rectangular Robust Markov Decision Processes [49.05403412954533]
  We present an efficient robust value iteration for texttts-rectangular robust Markov Decision Processes (MDPs) We do so by deriving the optimal robust Bellman operator in concrete forms using our $L_p$ water filling lemma. We unveil the exact form of the optimal policies, which turn out to be novel threshold policies with the probability of playing an action proportional to its advantage.
  arXiv  Detail & Related papers  (2023-01-31T13:54:23Z)
• Nearly Optimal Latent State Decoding in Block MDPs [74.51224067640717]
  In episodic Block MDPs, the decision maker has access to rich observations or contexts generated from a small number of latent states. We are first interested in estimating the latent state decoding function based on data generated under a fixed behavior policy. We then study the problem of learning near-optimal policies in the reward-free framework.
  arXiv  Detail & Related papers  (2022-08-17T18:49:53Z)
• Near-Optimal Sample Complexity Bounds for Constrained MDPs [25.509556551558834]
  We provide minimax upper and lower bounds on the sample complexity for learning near-optimal policies in a discounted CMDP. We show that learning CMDPs is as easy as MDPs when small constraint violations are allowed, but inherently more difficult when we demand zero constraint violation.
  arXiv  Detail & Related papers  (2022-06-13T15:58:14Z)
• Efficient Policy Iteration for Robust Markov Decision Processes via Regularization [49.05403412954533]
  Robust decision processes (MDPs) provide a framework to model decision problems where the system dynamics are changing or only partially known. Recent work established the equivalence between texttts rectangular $L_p$ robust MDPs and regularized MDPs, and derived a regularized policy iteration scheme that enjoys the same level of efficiency as standard MDPs. In this work, we focus on the policy improvement step and derive concrete forms for the greedy policy and the optimal robust Bellman operators.
  arXiv  Detail & Related papers  (2022-05-28T04:05:20Z)
• Adaptive Sampling for Best Policy Identification in Markov Decision Processes [79.4957965474334]
  We investigate the problem of best-policy identification in discounted Markov Decision (MDPs) when the learner has access to a generative model. The advantages of state-of-the-art algorithms are discussed and illustrated.
  arXiv  Detail & Related papers  (2020-09-28T15:22:24Z)
• 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)
• Provably Efficient Model-Free Algorithm for MDPs with Peak Constraints [38.2783003051101]
  This paper considers the peak Constrained Markov Decision Process (PCMDP), where the agent chooses the policy to maximize total reward in the finite horizon as well as satisfy constraints at each epoch with probability 1. We propose a model-free algorithm that converts PCMDP problem to an unconstrained problem and a Q-learning based approach is applied.
  arXiv  Detail & Related papers  (2020-03-11T23:23:29Z)
• Provably Efficient Safe Exploration via Primal-Dual Policy Optimization [105.7510838453122]
  We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation. We present an provably efficient online policy optimization algorithm for CMDP with safe exploration in the function approximation setting.
  arXiv  Detail & Related papers  (2020-03-01T17:47:03Z)

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.