Pith. sign in

REVIEW 6 cited by

Exploration-Exploitation in Constrained MDPs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2003.02189 v1 pith:4APG6YXT submitted 2020-03-04 cs.LG stat.ML

classification cs.LGstat.ML
keywords whileapproachformulationlearningagentcmdpcmdpsconstraints
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In many sequential decision-making problems, the goal is to optimize a utility function while satisfying a set of constraints on different utilities. This learning problem is formalized through Constrained Markov Decision Processes (CMDPs). In this paper, we investigate the exploration-exploitation dilemma in CMDPs. While learning in an unknown CMDP, an agent should trade-off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward while satisfying the constraints. While the agent will eventually learn a good or optimal policy, we do not want the agent to violate the constraints too often during the learning process. In this work, we analyze two approaches for learning in CMDPs. The first approach leverages the linear formulation of CMDP to perform optimistic planning at each episode. The second approach leverages the dual formulation (or saddle-point formulation) of CMDP to perform incremental, optimistic updates of the primal and dual variables. We show that both achieves sublinear regret w.r.t.\ the main utility while having a sublinear regret on the constraint violations. That being said, we highlight a crucial difference between the two approaches; the linear programming approach results in stronger guarantees than in the dual formulation based approach.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 31 citations worldwide. Full citation record

  1. Decoupling Corruption and Horizon in Robust Contextual Pricing

    cs.GT 2026-07 accept novelty 7.0 of 10

    Robust contextual pricing admits regret O(Cd + d² log T), the first bound that additively separates corruption budget C from horizon T.

  2. Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints

    cs.LG 2025-09 conditional novelty 6.0 of 10

    A new algorithm achieves Õ(√T) regret and constraint violation in online CMDPs without Slater's condition, plus sublinear α-regret against the unconstrained optimum under adversarial constraints.

  3. Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning

    cs.AI 2025-08 conditional novelty 6.0 of 10

    A new RL reward-shaping method that rewards low confidence on hard problems and high confidence on easy ones improves LLM math reasoning over a GRPO baseline.

  4. No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Given a spending plan, primal-dual no-regret algorithms achieve tilde-O(sqrt T) dynamic or static regret under adversarially changing reward and cost distributions, and tilde-O(T^{3/4}) when the plan is highly imbalanced.

  5. Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guarantees

    cs.LG 2025-08 unverdicted novelty 5.0 of 10

    Two new Monte Carlo tree search algorithms, CVaR-MCTS and W-MCTS, give provable PAC-level tail-risk controls and regret bounds for worst-case outcome scenarios.

  6. An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints

    cs.LG 2025-05 reject novelty 5.0 of 10

    A primal-dual algorithm with optimistic mirror descent is claimed to achieve O~(sqrt K) regret and O~(sqrt K) strong constraint violation in episodic CMDPs with anytime adversarial constraints, without Slater's condition.

Pith tools