English
Related papers

Related papers: A Contractive Feedback Semantics for Reinforcement…

200 papers

A key impediment to reinforcement learning (RL) in real applications with limited, batch data is defining a reward function that reflects what we implicitly know about reasonable behaviour for a task and allows for robust off-policy…

Machine Learning · Computer Science 2019-05-31 Niranjani Prasad , Barbara E Engelhardt , Finale Doshi-Velez

How do language models "think"? This paper formulates a probabilistic cognitive model called the bounded pragmatic speaker, which can characterize the operation of different variations of language models. Specifically, we demonstrate that…

Computation and Language · Computer Science 2024-01-03 Khanh Nguyen

We provide a control-theoretic perspective on optimal tensor algorithms for minimizing a convex function in a finite-dimensional Euclidean space. Given a function $\Phi: \mathbb{R}^d \rightarrow \mathbb{R}$ that is convex and twice…

Optimization and Control · Mathematics 2026-01-21 Tianyi Lin , Michael. I. Jordan

Reinforcement learning from human feedback (RLHF) has been widely adopted to align language models (LMs) with human preference. Prior RLHF works typically take a bandit formulation, which, though intuitive, ignores the sequential nature of…

Computation and Language · Computer Science 2025-01-07 Yueqin Yin , Shentao Yang , Yujia Xie , Ziyi Yang , Yuting Sun , Hany Awadalla , Weizhu Chen , Mingyuan Zhou

We present a stochastic predictive controller for discrete time linear time invariant systems under incomplete state information. Our approach is based on a suitable choice of control policies, stability constraints, and employment of a…

Optimization and Control · Mathematics 2018-02-27 Prabhat Kumar Mishra , Debasish Chatterjee , Daniel E. Quevedo

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…

Machine Learning · Computer Science 2026-05-26 Fei Ding , Yongkang Zhang , youwei wang , Zijian Zeng

Large Language Models employing Chain-of-Thought reasoning achieve strong performance but suffer from excessive token consumption that inflates inference costs. Existing efficiency methods such as explicit length penalties, difficulty…

Machine Learning · Computer Science 2026-04-03 Bangji Yang , Hongbo Ma , Jiajun Fan , Ge Liu

Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL). Finite sample guarantees for these methods often crucially rely on two types of assumptions: (1) mild distribution…

Machine Learning · Computer Science 2019-05-02 Jinglin Chen , Nan Jiang

We introduce the framework of performative reinforcement learning where the policy chosen by the learner affects the underlying reward and transition dynamics of the environment. Following the recent literature on performative…

Machine Learning · Computer Science 2023-06-08 Debmalya Mandal , Stelios Triantafyllou , Goran Radanovic

Recently, there has been a surge in interest in safe and robust techniques within reinforcement learning (RL). Current notions of risk in RL fail to capture the potential for systemic failures such as abrupt stoppages from system failures…

Systems and Control · Computer Science 2019-10-09 David Mguni

We demonstrate that a wide array of machine learning algorithms are specific instances of one single paradigm: reciprocal learning. These instances range from active learning over multi-armed bandits to self-training. We show that all these…

Machine Learning · Statistics 2024-11-05 Julian Rodemann , Christoph Jansen , Georg Schollmeyer

Closed-loop reference models have recently been proposed for states accessible adaptive systems. They have been shown to have improved transient response over their open loop counter parts. The results in the states accessible case are…

Optimization and Control · Mathematics 2012-11-29 Travis E. Gibson , Anuradha M. Annaswamy , Eugene Lavretsky

Commonly in reinforcement learning (RL), rewards are discounted over time using an exponential function to model time preference, thereby bounding the expected long-term reward. In contrast, in economics and psychology, it has been shown…

Machine Learning · Computer Science 2022-12-08 Matthias Schultheis , Constantin A. Rothkopf , Heinz Koeppl

Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of the recovered reward:…

Machine Learning · Statistics 2025-12-09 Denis Belomestny , Alexey Naumov , Sergey Samsonov

Ensuring that reinforcement learning (RL) controllers satisfy safety and reliability constraints in real-world settings remains challenging: state-avoidance and constrained Markov decision processes often fail to capture trajectory-level…

Machine Learning · Computer Science 2026-04-06 Alper Kamil Bozkurt , Calin Belta , Ming C. Lin

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…

Machine Learning · Computer Science 2021-12-22 Tom Bewley , Freddy Lecue

Recently, there has been a surge of research on a class of methods called feedback optimization. These are methods to steer the state of a control system to an equilibrium that arises as the solution of an optimization problem. Despite the…

Optimization and Control · Mathematics 2026-02-18 Giannis Delimpaltadakis , Pol Mestres , Jorge Cortés , W. P. M. H. Heemels

This work studies the design problem of feedback stabilizers for discrete-time systems with input delays. A backstepping procedure is proposed for disturbance-free discrete-time systems. The feedback law designed by using backstepping…

Optimization and Control · Mathematics 2012-12-05 Iasson Karafyllis , Miroslav Krstic

Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit states and actions…

Machine Learning · Computer Science 2020-07-23 Yao Liu , Adith Swaminathan , Alekh Agarwal , Emma Brunskill

We devise a control-theoretic reinforcement learning approach to support direct learning of the optimal policy. We establish various theoretical properties of our approach, such as convergence and optimality of our analog of the Bellman…

Machine Learning · Computer Science 2026-04-01 Weiqin Chen , Mark S. Squillante , Chai Wah Wu , Santiago Paternain