English
Related papers

Related papers: Muesli: Combining Improvements in Policy Optimizat…

200 papers

Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…

Machine Learning · Computer Science 2026-03-31 Gaurav Chaudhary , Laxmidhar Behera , Washim Uddin Mondal

The major challenge of offline RL is the distribution shift that appears when out-of-distribution actions are queried, which makes the policy improvement direction biased by extrapolation errors. Most existing methods address this problem…

Machine Learning · Computer Science 2024-02-29 Xiao Ma , Bingyi Kang , Zhongwen Xu , Min Lin , Shuicheng Yan

A precondition for the deployment of a Reinforcement Learning agent to a real-world system is to provide guarantees on the learning process. While a learning algorithm will eventually converge to a good policy, there are no guarantees on…

Machine Learning · Statistics 2023-12-27 Paul Daoudi , Mathias Formoso , Othman Gaizi , Achraf Azize , Evrard Garcelon

We present Residual Policy Learning (RPL): a simple method for improving nondifferentiable policies using model-free deep reinforcement learning. RPL thrives in complex robotic manipulation tasks where good but imperfect controllers are…

Robotics · Computer Science 2019-01-04 Tom Silver , Kelsey Allen , Josh Tenenbaum , Leslie Kaelbling

Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and…

Machine Learning · Computer Science 2025-04-22 Hikaru Shindo , Quentin Delfosse , Devendra Singh Dhami , Kristian Kersting

This paper addresses policy learning in non-stationary environments and games with continuous actions. Rather than the classical reward maximization mechanism, inspired by the ideas of follow-the-regularized-leader (FTRL) and mirror descent…

Machine Learning · Computer Science 2022-08-22 Rong-Jun Qin , Fan-Ming Luo , Hong Qian , Yang Yu

We consider online imitation learning (OIL), where the task is to find a policy that imitates the behavior of an expert via active interaction with the environment. We aim to bridge the gap between the theory and practice of policy…

Machine Learning · Computer Science 2022-08-02 Jonathan Wilder Lavington , Sharan Vaswani , Mark Schmidt

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

Machine Learning · Computer Science 2025-08-07 Jinghang Han , Jiawei Chen , Hang Shao , Hao Ma , Mingcheng Li , Xintian Shen , Lihao Zheng , Wei Chen , Tao Wei , Lihua Zhang

Nonlinear attitude filters have been recognized to have simpler structure and better tracking performance when compared with Gaussian attitude filters and other methods of attitude determination. A key element of nonlinear attitude filter…

Systems and Control · Electrical Eng. & Systems 2021-09-13 Ajay Singh , Trenton S. Sieb , James H. Howe , Hashim A. Hashim

We propose a new approach to visualize saliency maps for deep neural network models and apply it to deep reinforcement learning agents trained on Atari environments. Our method adds an attention module that we call FLS (Free Lunch Saliency)…

Machine Learning · Computer Science 2019-11-01 Dmitry Nikulin , Anastasia Ianina , Vladimir Aliev , Sergey Nikolenko

G\"odel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, a G\"odel agent for compact models that performs policy repair via…

Machine Learning · Computer Science 2026-05-15 Aditya Kakade , Vivek Srivastava , Shirish Karande

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim…

Machine Learning · Computer Science 2019-06-11 Zafarali Ahmed , Nicolas Le Roux , Mohammad Norouzi , Dale Schuurmans

We consider the task of building strong but human-like policies in multi-agent decision-making problems, given examples of human behavior. Imitation learning is effective at predicting human actions but may not match the strength of expert…

Multiagent Systems · Computer Science 2022-02-18 Athul Paul Jacob , David J. Wu , Gabriele Farina , Adam Lerer , Hengyuan Hu , Anton Bakhtin , Jacob Andreas , Noam Brown

One of the most interesting features of Bayesian optimization for direct policy search is that it can leverage priors (e.g., from simulation or from previous tasks) to accelerate learning on a robot. In this paper, we are interested in…

Robotics · Computer Science 2018-03-14 Rémi Pautrat , Konstantinos Chatzilygeroudis , Jean-Baptiste Mouret

Discovering improved policy optimization algorithms for language models remains a costly manual process requiring repeated mechanism-level modification and validation. Unlike simple combinatorial code search, this problem requires searching…

Computation and Language · Computer Science 2026-03-26 Sirui Xia , Yikai Zhang , Aili Chen , Siye Wu , Siyu Yuan , Yanghua Xiao

Online imitation learning (IL) is an algorithmic framework that leverages interactions with expert policies for efficient policy optimization. Here policies are optimized by performing online learning on a sequence of loss functions that…

Machine Learning · Computer Science 2021-02-23 Xinyan Yan , Byron Boots , Ching-An Cheng

Developing generalist systems that retain human-like data efficiency is a central challenge. While world models (WMs) offer a promising path, existing research often conflates architectural mechanisms with the independent impact of model…

Machine Learning · Computer Science 2026-05-12 Jooyeon Kim

Reinforcement Learning (RL) offers a promising solution to enable evolutionary automated driving. However, the conventional RL method is always concerned with risk performance. The updated policy may not obtain a performance enhancement,…

Systems and Control · Electrical Eng. & Systems 2024-12-17 Jia Hu , Xuerun Yan , Tian Xu , Haoran Wang

Sequential decision-making under uncertainty is present in many important problems. Two popular approaches for tackling such problems are reinforcement learning and online search (e.g., Monte Carlo tree search). While the former learns a…

Artificial Intelligence · Computer Science 2024-01-23 Ava Pettet , Yunuo Zhang , Baiting Luo , Kyle Wray , Hendrik Baier , Aron Laszka , Abhishek Dubey , Ayan Mukhopadhyay

Reinforcement learning (RL) has emerged as a powerful tool for fine-tuning large language models (LLMs) to improve complex reasoning abilities. However, state-of-the-art policy optimization methods often suffer from high computational…

Machine Learning · Computer Science 2025-05-28 Kianté Brantley , Mingyu Chen , Zhaolin Gao , Jason D. Lee , Wen Sun , Wenhao Zhan , Xuezhou Zhang