English
Related papers

Related papers: Reward Scale Robustness for Proximal Policy Optimi…

200 papers

In pursuit of enhanced multi-agent collaboration, we analyze several on-policy deep reinforcement learning algorithms in the recently published Hanabi benchmark. Our research suggests a perhaps counter-intuitive finding, where Proximal…

Machine Learning · Computer Science 2022-03-23 Bram Grooten , Jelle Wemmenhove , Maurice Poot , Jim Portegies

Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games. However, recent advancements in game AI based on reinforcement learning have predominantly focused on improving proficiency,…

Artificial Intelligence · Computer Science 2025-09-23 Lingfeng Li , Yunlong Lu , Yongyi Wang , Wenxin Li

We consider the Reinforcement Learning problem of controlling an unknown dynamical system to maximise the long-term average reward along a single trajectory. Most of the literature considers system interactions that occur in discrete time…

Artificial Intelligence · Computer Science 2023-09-07 Lorenzo Croissant , Marc Abeille , Bruno Bouchard

Reinforcement Learning (RL) with PPO-like clip objectives has become the standard choice for reward-based fine-tuning of large language models (LLMs). Although recent work has explored improved estimators of advantages and normalization,…

Machine Learning · Computer Science 2026-02-24 Philipp Becker , Niklas Freymuth , Serge Thilges , Fabian Otto , Gerhard Neumann

Fairness in multi-agent systems (MAS) focuses on equitable reward distribution among agents in scenarios involving sensitive attributes such as race, gender, or socioeconomic status. This paper introduces fairness in Proximal Policy…

Multiagent Systems · Computer Science 2025-09-03 Gabriele La Malfa , Jie M. Zhang , Michael Luck , Elizabeth Black

This study investigates the effectiveness of reinforcement learning (RL) fine-tuning techniques on a compact language model (Qwen2.5-0.5B Base) for two challenging tasks: instruction following and mathematical reasoning. We compare…

Computation and Language · Computer Science 2025-07-29 Yifu Han , Geo Zhang

Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…

Machine Learning · Computer Science 2020-01-01 Aviral Kumar , Xue Bin Peng , Sergey Levine

Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of…

Machine Learning · Computer Science 2025-10-14 Mingyang Lyu , Yinqian Sun , Erliang Lin , Huangrui Li , Ruolin Chen , Feifei Zhao , Yi Zeng

Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal…

Machine Learning · Computer Science 2018-02-27 Ashvin Nair , Bob McGrew , Marcin Andrychowicz , Wojciech Zaremba , Pieter Abbeel

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning capabilities of large language models. However, existing approaches such as GRPO often suffer from zero gradients. This…

Computation and Language · Computer Science 2025-09-09 Shihui Yang , Chengfeng Dou , Peidong Guo , Kai Lu , Qiang Ju , Fei Deng , Rihui Xin

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Efficient truck dispatching via Reinforcement Learning (RL) in open-pit mining is often hindered by reliance on complex reward engineering and value-based methods. This paper introduces Curriculum-inspired Adaptive Direct Policy Guidance, a…

Machine Learning · Computer Science 2025-03-03 Shi Meng , Bin Tian , Xiaotong Zhang

Reinforcement learning has become a central paradigm for improving LLM reasoning. However, existing methods use a single policy to produce both inference responses and training optimization trajectories. The objective conflict between…

Machine Learning · Computer Science 2026-01-26 Jingchu Wang , Bingbing Xu , Yige Yuan , Bin Xie , Xiaoqian Sun , Huawei Shen

Deep reinforcement learning (DRL) has emerged as a powerful framework for solving sequential decision-making problems, achieving remarkable success in a wide range of applications, including game AI, autonomous driving, biomedicine, and…

Machine Learning · Computer Science 2025-05-14 Yinghan Sun , Hongxi Wang , Hua Chen , Wei Zhang

Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models hinges on baseline estimation for variance reduction, but existing approaches pay a heavy price: PPO requires a policy-model scale critic, while GRPO needs…

Machine Learning · Computer Science 2026-05-12 Yunho Choi , Jongwon Lim , Woojin Ahn , Minjae Oh , Jeonghoon Shim , Yohan Jo

In this paper, we propose a new algorithm PPG (Proximal Policy Gradient), which is close to both VPG (vanilla policy gradient) and PPO (proximal policy optimization). The PPG objective is a partial variation of the VPG objective and the…

Machine Learning · Computer Science 2020-10-21 Ju-Seung Byun , Byungmoon Kim , Huamin Wang

Aligning large language models (LLMs) with human preferences has gained significant attention, with Proximal Policy Optimization (PPO) as a standard yet computationally expensive method and Direct Preference Optimization (DPO) as a more…

Artificial Intelligence · Computer Science 2025-02-10 Yuzi Yan , Yibo Miao , Jialian Li , Yipin Zhang , Jian Xie , Zhijie Deng , Dong Yan

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied…

Machine Learning · Computer Science 2024-05-06 Zhongchang Sun , Sihong He , Fei Miao , Shaofeng Zou

Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get…

Machine Learning · Computer Science 2020-01-13 Kai Jiang , XiaoLong Qin
‹ Prev 1 8 9 10 Next ›