English
Related papers

Related papers: Eventual Discounting Temporal Logic Counterfactual…

200 papers

In this paper, we propose a model-free reinforcement learning method to synthesize control policies for motion planning problems with continuous states and actions. The robot is modelled as a labeled discrete-time Markov decision process…

Artificial Intelligence · Computer Science 2020-10-01 Chuanzheng Wang , Yinan Li , Stephen L. Smith , Jun Liu

In experimenting with off-policy temporal difference (TD) methods in hierarchical reinforcement learning (HRL) systems, we have observed unwanted on-policy learning under reproducible conditions. Here we present modifications to several TD…

Machine Learning · Computer Science 2015-03-19 Mitchell Keith Bloch

We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. To this end we apply empirical likelihood techniques to formulate our estimator and confidence…

Machine Learning · Computer Science 2020-10-20 Nikos Karampatziakis , John Langford , Paul Mineiro

Scaling test-time compute is crucial for enhancing the reasoning capabilities of large language models (LLMs). Existing approaches typically employ reinforcement learning (RL) to maximize a verifiable reward obtained at the end of reasoning…

Machine Learning · Computer Science 2025-11-10 Penghui Qi , Zichen Liu , Tianyu Pang , Chao Du , Wee Sun Lee , Min Lin

We present a computational framework for synthesis of distributed control strategies for a heterogeneous team of robots in a partially observable environment. The goal is to cooperatively satisfy specifications given as Truncated Linear…

Artificial Intelligence · Computer Science 2022-04-07 Ningyuan Zhang , Wenliang Liu , Calin Belta

Many modern commercial sites employ recommender systems to propose relevant content to users. While most systems are focused on maximizing the immediate gain (clicks, purchases or ratings), a better notion of success would be the lifetime…

Machine Learning · Statistics 2017-02-24 Assaf Hallak , Yishay Mansour , Elad Yom-Tov

Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch between the optimization space and the structure of…

Machine Learning · Computer Science 2026-05-19 Haoqiang Kang , Yizhe Zhang , Nikki Lijing Kuang , Yi-An Ma , Lianhui Qin

Recent advances in Reinforcement Learning (RL) largely benefit from the inclusion of Deep Neural Networks, boosting the number of novel approaches proposed in the field of Deep Reinforcement Learning (DRL). These techniques demonstrate the…

Machine Learning · Computer Science 2025-07-30 Giovanni Dispoto , Paolo Bonetti , Marcello Restelli

In this paper, we present a novel RRT*-based strategy for generating kinodynamically feasible paths that satisfy temporal logic specifications. Our approach integrates a robustness metric for Linear Temporal Logics (LTL) with the system's…

Systems and Control · Electrical Eng. & Systems 2024-11-12 Saksham Gautam , Ratnangshu Das , Pushpak Jagtap

Autonomous agents often operate in scenarios where the state is partially observed. In addition to maximizing their cumulative reward, agents must execute complex tasks with rich temporal and logical structures. These tasks can be expressed…

Systems and Control · Electrical Eng. & Systems 2022-03-18 Krishna C. Kalagarla , Dhruva Kartik , Dongming Shen , Rahul Jain , Ashutosh Nayyar , Pierluigi Nuzzo

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

In order for humans to confidently decide where to employ RL agents for real-world tasks, a human developer must validate that the agent will perform well at test-time. Some policy interpretability methods facilitate this by capturing the…

Machine Learning · Computer Science 2022-03-22 Julius Frost , Olivia Watkins , Eric Weiner , Pieter Abbeel , Trevor Darrell , Bryan Plummer , Kate Saenko

Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to reach the goal quickly, and LRM reasoning can be viewed…

Machine Learning · Computer Science 2026-05-27 Alex Ayoub , Kavosh Asadi , Dale Schuurmans , Csaba Szepesvári , Karim Bouyarmane

Policy-based methods currently dominate reinforcement learning (RL) pipelines for large language model (LLM) reasoning, leaving value-based approaches largely unexplored. We revisit the classical paradigm of Bellman Residual Minimization…

Machine Learning · Computer Science 2025-11-13 Yurun Yuan , Fan Chen , Zeyu Jia , Alexander Rakhlin , Tengyang Xie

Learning from demonstration (LfD) has succeeded in tasks featuring a long time horizon. However, when the problem complexity also includes human-in-the-loop perturbations, state-of-the-art approaches do not guarantee the successful…

Robotics · Computer Science 2024-12-10 Yanwei Wang , Nadia Figueroa , Shen Li , Ankit Shah , Julie Shah

While Bellman equations for basic reach, avoid, and reach-avoid problems are well studied, the relationship between value optimality and policy optimality becomes subtle in the undiscounted infinite-horizon setting, particularly for more…

Robotics · Computer Science 2026-05-05 Oswin So , William Sharpless , Sylvia Herbert , Chuchu Fan

Reinforcement learning (RL) policies may exhibit unsafe behavior and are hard to explain. We use counterfactual large language model reasoning to enhance RL policy safety post-training. We show that our approach improves and helps to…

Machine Learning · Computer Science 2024-09-17 Dennis Gross , Helge Spieker

Reinforcement learning (RL) aims to estimate the action to take given a (time-varying) state, with the goal of maximizing a cumulative reward function. Predominantly, there are two families of algorithms to solve RL problems: value-based…

Machine Learning · Computer Science 2025-01-10 Sergio Rozada , Hoi-To Wai , Antonio G. Marques

Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions), and predicting their outcomes (prediction). This skill is…

Machine Learning · Computer Science 2025-10-03 Aniket Vashishtha , Qirun Dai , Hongyuan Mei , Amit Sharma , Chenhao Tan , Hao Peng

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse