English
Related papers

Related papers: General Exploratory Bonus for Optimistic Explorati…

200 papers

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major challenge. We identify two key obstacles to its mitigation:…

Machine Learning · Computer Science 2025-10-16 Yuchun Miao , Liang Ding , Sen Zhang , Rong Bao , Lefei Zhang , Dacheng Tao

Reinforcement Learning from Human Feedback (RLHF) is a widely used framework for the training of language models. However, the process of using RLHF to develop a language model that is well-aligned presents challenges, especially when it…

Computation and Language · Computer Science 2024-04-09 Bowen Qin , Duanyu Feng , Xi Yang

The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to…

Machine Learning · Computer Science 2019-09-10 Lior Shani , Yonathan Efroni , Shie Mannor

Large Language Models (LLMs) are emerging as promising tools for automated reinforcement learning (RL) reward design, owing to their robust capabilities in commonsense reasoning and code generation. By engaging in dialogues with RL agents,…

Artificial Intelligence · Computer Science 2025-04-14 Zen Kit Heng , Zimeng Zhao , Tianhao Wu , Yuanfei Wang , Mingdong Wu , Yangang Wang , Hao Dong

Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic…

Machine Learning · Computer Science 2019-06-14 Hyoungseok Kim , Jaekyeom Kim , Yeonwoo Jeong , Sergey Levine , Hyun Oh Song

We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle. In particular, we do not assume the existence of a reward function and an oracle preference signal drawn from the Bradley-Terry…

Machine Learning · Computer Science 2024-11-13 Chenlu Ye , Wei Xiong , Yuheng Zhang , Hanze Dong , Nan Jiang , Tong Zhang

Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new…

Machine Learning · Computer Science 2020-02-10 Chi Jin , Akshay Krishnamurthy , Max Simchowitz , Tiancheng Yu

Exploration is essential for reinforcement learning (RL). To face the challenges of exploration, we consider a reward-free RL framework that completely separates exploration from exploitation and brings new challenges for exploration…

Machine Learning · Computer Science 2020-12-11 Chuheng Zhang , Yuanying Cai , Longbo Huang , Jian Li

Deep reinforcement learning was instigated with the presence of trust region methods, being scalable and efficient. However, the pessimism of such algorithms, among which it forces to constrain in a trust region by all means, has been…

Machine Learning · Computer Science 2023-03-06 Jianfei Ma

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

Machine Learning · Computer Science 2024-12-24 Akane Tsuboya , Yu Kono , Tatsuji Takahashi

In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty. However, in the presence of environmental…

Machine Learning · Computer Science 2023-12-21 Jinyi Liu , Zhi Wang , Yan Zheng , Jianye Hao , Chenjia Bai , Junjie Ye , Zhen Wang , Haiyin Piao , Yang Sun

Exploration efficiency poses a significant challenge in goal-conditioned reinforcement learning (GCRL) tasks, particularly those with long horizons and sparse rewards. A primary limitation to exploration efficiency is the agent's inability…

Machine Learning · Computer Science 2024-04-22 Lisheng Wu , Ke Chen

Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper…

Machine Learning · Computer Science 2021-02-16 Yuping Luo , Huazhe Xu , Yuanzhi Li , Yuandong Tian , Trevor Darrell , Tengyu Ma

We consider reinforcement learning (RL) in continuous time and study the problem of achieving the best trade-off between exploration of a black box environment and exploitation of current knowledge. We propose an entropy-regularized reward…

Optimization and Control · Mathematics 2019-02-14 Haoran Wang , Thaleia Zariphopoulou , Xunyu Zhou

Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Optimization (GRPO) serving as the dominant algorithm. We identify two overlooked…

Machine Learning · Computer Science 2026-05-13 Mingxiong Lin , Zhangquan Gong , Maowen Tang , Qian Li , Chuangchuang Wang , Jian Ma , Sutian Huang , Kai Tang , Haonan Lu

In classic Reinforcement Learning (RL), the agent maximizes an additive objective of the visited states, e.g., a value function. Unfortunately, objectives of this type cannot model many real-world applications such as experiment design,…

Machine Learning · Computer Science 2024-07-16 Riccardo De Santi , Manish Prajapat , Andreas Krause

Model-based deep reinforcement learning has achieved success in various domains that require high sample efficiencies, such as Go and robotics. However, there are some remaining issues, such as planning efficient explorations to learn more…

Machine Learning · Computer Science 2021-07-06 Yao Yao , Li Xiao , Zhicheng An , Wanpeng Zhang , Dijun Luo

Post-training techniques combined with inference-time scaling significantly enhance the reasoning and alignment capabilities of large language models (LLMs). However, a fundamental tension arises: inference-time methods benefit from diverse…

Machine Learning · Computer Science 2026-05-12 Changhao Li , Yuchen Zhuang , Chenxiao Gao , Haotian Sun , Rushi Qiang , Chao Zhang , Bo Dai

Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot…

Machine Learning · Computer Science 2022-03-04 Simone Parisi , Davide Tateo , Maximilian Hensel , Carlo D'Eramo , Jan Peters , Joni Pajarinen