paper-with-me

Papers

A Contractive Feedback Semantics for Reinforcement Learning

2026-05-23 · Zuyuan Zhang arxiv

Discounted reinforcement learning is usually presented through Bellman equations on closed Markov decision processes. This paper develops a compositional view: a one-step decision process is treated as an open stochastic component, and infinite-horizon policy evaluation is obtained by closing a contractive feedback loop. The resulting semantics assigns typed Bellman transformers to open components, interprets series and parallel wiring as composition and tensoring of transformers, and interprets feedback as an admissible guarded Banach trace realized by a unique fixed point. This perspective yields three theoretical consequences. First, approximate component equivalence is a contextual congruence for admitted well-typed guarded one-hole contexts: local operator error remains controlled after plugging the component into a surrounding circuit that uses the hole once and whose feedback nodes have certified uniform guardedness. Second, exact and approximate state abstractions become commuting or near-commuting coalgebraic diagrams, giving value-preservation and explicit sup-norm distortion bounds. Third, under monotone $ω$-continuous contract-transformer semantics, safety, risk, and resource specifications can be represented as quantale-valued contracts, where local inductive bounds lift through wiring and feedback by least-fixed-point reasoning. Its central claim is not that all RL morphisms form a global traced monoidal category, but that discounted Bellman evaluation admits a contractive feedback semantics on the admissible class of guarded circuits.

📄 PDF Abstract BibTeX arXiv:2605.24759

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning

2026-03-10 · Zhanyi Sun, Shuran Song arxiv

We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a "distribution contraction" operator to refine pretrained generative robot policies. DICE-RL t…

Reinforcement LearningSkill Mastery

Safe-EF: Error Feedback for Nonsmooth Constrained Optimization

2025-05-09 · Rustem Islamov, Yarden As, Ilyas Fatkhullin

Federated learning faces severe communication bottlenecks due to the high dimensionality of model updates. Communication compression with contractive compressors (e.g., Top-K) is often preferable in practice but can degr…

Federated Learning

Concentration of Contractive Stochastic Approximation and Reinforcement Learning

2021-06-27 · Siddharth Chandak, Vivek S. Borkar, Parth Dodhia

Using a martingale concentration inequality, concentration bounds `from time $n_0$ on' are derived for stochastic approximation algorithms with contractive maps and both martingale difference and Markov noises. These are…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Accelerated Distributed Optimization with Compression and Error Feedback

2025-03-11 · Yuan Gao, Anton Rodomanov, Jeremy Rack, Sebastian U. Stich

Modern machine learning tasks often involve massive datasets and models, necessitating distributed optimization algorithms with reduced communication overhead. Communication compression, where clients transmit compressed…

Distributed Optimization

A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning

2020-06-19 · ICLR 2021 1 · Samuel Horváth, Peter Richtárik

Modern large-scale machine learning applications require stochastic optimization algorithms to be implemented on distributed compute systems. A key bottleneck of such systems is the communication overhead for exchanging …

Federated LearningStochastic Optimization