pith. sign in

arxiv: 2312.16730 · v1 · pith:5END7BQInew · submitted 2023-12-27 · 💻 cs.LG · math.OC· math.ST· stat.ML· stat.TH

Foundations of Reinforcement Learning and Interactive Decision Making

classification 💻 cs.LG math.OCmath.STstat.MLstat.TH
keywords learningdecisionmakingreinforcementbanditsfoundationsinteractiveaddressing
0
0 comments X
read the original abstract

These lecture notes give a statistical perspective on the foundations of reinforcement learning and interactive decision making. We present a unifying framework for addressing the exploration-exploitation dilemma using frequentist and Bayesian approaches, with connections and parallels between supervised learning/estimation and decision making as an overarching theme. Special attention is paid to function approximation and flexible model classes such as neural networks. Topics covered include multi-armed and contextual bandits, structured bandits, and reinforcement learning with high-dimensional feedback.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon

    cs.LG 2026-06 unverdicted novelty 7.0

    Online IL overcomes an information-theoretic bottleneck that offline IL faces in non-realizable settings even at horizon 1, under a new structural characterization of reward-relative misspecification.

  2. Efficient Exploration for Iterative Nash Preference Optimization

    cs.LG 2026-05 unverdicted novelty 7.0

    An explicitly exploratory iterative NLHF method achieves O(sqrt(T)) regret for Nash equilibria under general preference models, removing the exponential KL dependence that plagues standard iterative approaches.

  3. Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability

    cs.LG 2026-05 unverdicted novelty 7.0

    The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general functi...

  4. Constrained Contextual Bandits with Adversarial Contexts

    cs.LG 2026-05 unverdicted novelty 7.0

    A modular reduction from budget-constrained contextual bandits with adversarial contexts to unconstrained bandits via surrogate rewards, yielding improved guarantees and an efficient algorithm based on SquareCB.

  5. When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?

    stat.ML 2026-06 unverdicted novelty 6.0

    Proposes OPAC for trajectory-level offline RL achieving 𝓣O(H^{2}√(C_sa(π*)/n)) bounds with matching lower bound, plus conditions for tractability in generalized nonlinear outcome settings.

  6. Improved Guarantees for Constrained Online Convex Optimization via Self-Contraction

    cs.LG 2026-05 unverdicted novelty 6.0

    A projection-based algorithm for COCO achieves O(log T) regret and O(log T) CCV for strongly convex losses and O(sqrt(T)) for convex losses by leveraging self-contracted curves.