English
Related papers

Related papers: Monotone and Conservative Policy Iteration Beyond …

200 papers

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…

Machine Learning · Computer Science 2024-09-17 Shashank Gupta , Harrie Oosterhuis , Maarten de Rijke

Markov games and robust MDPs are closely related models that involve computing a pair of saddle point policies. As part of the long-standing effort to develop efficient algorithms for these models, the Filar-Tolwinski (FT) algorithm has…

Computer Science and Game Theory · Computer Science 2025-11-18 Keith Badger , Jefferson Huang , Marek Petrik

Reinforcement learning algorithms solve sequential decision-making problems in probabilistic environments by optimizing for long-term reward. The desire to use reinforcement learning in safety-critical settings inspires a recent line of…

Artificial Intelligence · Computer Science 2020-12-17 Koundinya Vajjha , Avraham Shinnar , Vasily Pestun , Barry Trager , Nathan Fulton

We consider approximate dynamic programming for the infinite-horizon stationary $\gamma$-discounted optimal control problem formalized by Markov Decision Processes. While in the exact case it is known that there always exists an optimal…

Optimization and Control · Mathematics 2013-04-23 Boris Lesner , Bruno Scherrer

In this paper we propose a novel decision making architecture for Robust Model Predictive Path Integral control (RMPPI) and investigate its performance guarantees and applicability to off-road navigation. Key building blocks of the proposed…

Systems and Control · Electrical Eng. & Systems 2021-02-19 Manan Gandhi , Bogdan Vlahov , Jason Gibson , Grady Williams , Evangelos A. Theodorou

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Machine Learning · Computer Science 2017-08-29 John Schulman , Filip Wolski , Prafulla Dhariwal , Alec Radford , Oleg Klimov

This paper presents a systematic framework for computing formally guaranteed trajectory tracking error bounds for autonomous helicopters based on Robust Positive Invariant (RPI) sets. The approach focuses on establishing a closed-loop…

Systems and Control · Electrical Eng. & Systems 2026-03-10 Philipp Schitz , Johann C. Dauer , Paolo Mercorelli

Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by…

Machine Learning · Computer Science 2021-03-18 Aldo Pacchiano , Jonathan Lee , Peter Bartlett , Ofir Nachum

This paper employs a policy iteration reinforcement learning (RL) method to study continuous-time linear-quadratic mean-field control problems in infinite horizon. The drift and diffusion terms in the dynamics involve the states, the…

Optimization and Control · Mathematics 2024-11-05 Na Li , Xun Li , Zuo Quan Xu

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

Robust Markov decision processes (MDPs) allow to compute reliable solutions for dynamic decision problems whose evolution is modeled by rewards and partially-known transition probabilities. Unfortunately, accounting for uncertainty in the…

Machine Learning · Computer Science 2020-06-18 Chin Pang Ho , Marek Petrik , Wolfram Wiesemann

One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates approximations to the optimal value function by solving a sequence of regression problems. To…

Machine Learning · Computer Science 2024-06-19 Noah Golowich , Ankur Moitra

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric…

Computation and Language · Computer Science 2026-05-26 Yihong Tang , Kehai Chen , Liang Yue , Benyou Wang , Min Zhang

In RL, given a prompt, we sample a group of completions from a model and score them. Two questions follow: which completions should gain probability mass, and how should the parameters move to realize that change? Standard policy-gradient…

Machine Learning · Computer Science 2026-04-08 Jean Kaddour

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training is often hindered by sparse binary rewards and weak credit…

Computation and Language · Computer Science 2026-05-15 Mengjie Ren , Jie Lou , Boxi Cao , Xueru Wen , Hongyu Lin , Xianpei Han , Le Sun , Xing Yu , Yaojie Lu

We study session-based recommendation scenarios where we want to recommend items to users during sequential interactions to improve their long-term utility. Optimizing a long-term metric is challenging because the learning signal (whether…

Machine Learning · Computer Science 2021-09-16 Bogdan Mazoure , Paul Mineiro , Pavithra Srinath , Reza Sharifi Sedeh , Doina Precup , Adith Swaminathan

In complex reinforcement learning (RL) problems, policies with similar rewards may have substantially different behaviors. It remains a fundamental challenge to optimize rewards while also discovering as many diverse strategies as possible,…

Machine Learning · Computer Science 2023-10-24 Wei Fu , Weihua Du , Jingwei Li , Sunli Chen , Jingzhao Zhang , Yi Wu

In this paper, we propose cautious policy programming (CPP), a novel value-based reinforcement learning (RL) algorithm that can ensure monotonic policy improvement during learning. Based on the nature of entropy-regularized RL, we derive a…

Machine Learning · Computer Science 2022-01-19 Lingwei Zhu , Toshinori Kitamura , Takamitsu Matsubara

In this work we address the problem of performing a repetitive task when we have uncertain observations and dynamics. We formulate this problem as an iterative infinite horizon optimal control problem with output feedback. Previously, this…

Systems and Control · Electrical Eng. & Systems 2021-10-04 Lukas Brunke , Siqi Zhou , Angela P. Schoellig

Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without further environment interaction. A key challenge is the distribution shift between the learned and behavior policies, leading to…

Machine Learning · Computer Science 2025-08-11 Haohui Chen , Zhiyong Chen