English
Related papers

Related papers: Provably Efficient Exploration in Policy Optimizat…

200 papers

Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks. While Direct Preference Optimization (DPO) has shown promise in…

Machine Learning · Computer Science 2024-12-30 Huaijie Wang , Shibo Hao , Hanze Dong , Shenao Zhang , Yilin Bao , Ziran Yang , Yi Wu

Policy optimization (PO) algorithms are used to refine Large Language Models for complex, multi-step reasoning. Current state-of-the-art pipelines enforce a strict think-then-answer format to elicit chain-of-thought (CoT); however, the…

Computation and Language · Computer Science 2025-10-28 Debdeep Sanyal , Aakash Sen Sharma , Dhruv Kumar , Saurabh Deshpande , Murari Mandal

The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…

Artificial Intelligence · Computer Science 2024-12-25 Jiacai Liu , Chaojie Wang , Chris Yuhao Liu , Liang Zeng , Rui Yan , Yiwen Sun , Yang Liu , Yahui Zhou

Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely shrink the exploration variance, which leads to slow progress…

Machine Learning · Computer Science 2020-11-04 Perttu Hämäläinen , Amin Babadi , Xiaoxiao Ma , Jaakko Lehtinen

In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial…

Computation and Language · Computer Science 2018-08-27 Yi-Lin Tuan , Jinzhi Zhang , Yujia Li , Hung-yi Lee

Proximal policy optimization(PPO) has been proposed as a first-order optimization method for reinforcement learning. We should notice that an exterior penalty method is used in it. Often, the minimizers of the exterior penalty functions…

Machine Learning · Computer Science 2018-12-18 Cheng Zeng , Hongming Zhang

Self-play, where the algorithm learns by playing against itself without requiring any direct supervision, has become the new weapon in modern Reinforcement Learning (RL) for achieving superhuman performance in practice. However, the…

Machine Learning · Computer Science 2020-07-10 Yu Bai , Chi Jin

Single-trajectory reinforcement learning (RL) methods aim to optimize policies from datasets consisting of (prompt, response, reward) triplets, where scalar rewards are directly available. This supervision format is highly practical, as it…

Machine Learning · Computer Science 2025-12-23 Bilal Faye , Hanane Azzag , Mustapha Lebbah

While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize ungrounded "lucky guesses," leaving the critical process of…

Artificial Intelligence · Computer Science 2026-04-21 Xin Guan , Zijian Li , Shen Huang , Pengjun Xie , Jingren Zhou , Jiuxin Cao

We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism principle and assuming that the MDP has a linear structure, we…

Machine Learning · Computer Science 2021-04-27 Chen-Yu Wei , Mehdi Jafarnia-Jahromi , Haipeng Luo , Rahul Jain

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…

Machine Learning · Computer Science 2018-12-27 Chen Tessler , Daniel J. Mankowitz , Shie Mannor

Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscriminately truncating high-return yet high-divergence updates. We demonstrate that explicitly…

Machine Learning · Computer Science 2026-05-27 Yu Luo , Shuo Han , Yihan Hu , Lei Lv , Huaping Liu , Fuchun Sun , Jianye Hao , Dong Li

The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…

Machine Learning · Computer Science 2023-05-01 Md Masudur Rahman , Yexiang Xue

Reinforcement learning (RL) in large or infinite state spaces is notoriously challenging, both theoretically (where worst-case sample and computational complexities must scale with state space cardinality) and experimentally (where function…

Machine Learning · Computer Science 2024-05-28 Marcel Hussing , Michael Kearns , Aaron Roth , Sikata Bela Sengupta , Jessica Sorrell

Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system…

Machine Learning · Computer Science 2025-09-12 Somnath Hazra , Pallab Dasgupta , Soumyajit Dey

On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…

Machine Learning · Computer Science 2025-11-13 Jianren Wang , Yifan Su , Abhinav Gupta , Deepak Pathak

We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…

Machine Learning · Computer Science 2022-06-27 Masatoshi Uehara , Ayush Sekhari , Jason D. Lee , Nathan Kallus , Wen Sun

The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human…

Machine Learning · Computer Science 2021-06-23 Zaynah Javed , Daniel S. Brown , Satvik Sharma , Jerry Zhu , Ashwin Balakrishna , Marek Petrik , Anca D. Dragan , Ken Goldberg

We consider the problem of reinforcement learning over episodes of a finite-horizon deterministic system and as a solution propose optimistic constraint propagation (OCP), an algorithm designed to synthesize efficient exploration and value…

Machine Learning · Computer Science 2016-07-08 Zheng Wen , Benjamin Van Roy

Uncertainty estimation for Reinforcement Learning (RL) is a critical component in control tasks where agents must balance safe exploration and efficient learning. While deep neural networks have enabled breakthroughs in RL, they often lack…

Machine Learning · Computer Science 2025-12-22 Matthijs van der Lende , Juan Cardenas-Cartagena