English
Related papers

Related papers: Beyond Fixed Morphologies: Learning Graph Policies…

200 papers

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.…

Machine Learning · Computer Science 2023-11-13 Jared Markowitz , Edward W. Staley

We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the 'center' of the…

Artificial Intelligence · Computer Science 2019-02-04 Yunhao Tang , Shipra Agrawal

Trust-region methods based on Kullback-Leibler divergence are pervasively used to stabilize policy optimization in reinforcement learning. In this paper, we exploit more flexible metrics and examine two natural extensions of policy…

Machine Learning · Computer Science 2023-06-27 Jun Song , Niao He , Lijun Ding , Chaoyue Zhao

Policy gradient reinforcement learning techniques enable an agent to directly learn an optimal action policy through the interactions with the environment. Nevertheless, despite its advantages, it sometimes suffers from slow convergence…

Information Theory · Computer Science 2020-08-05 Mohammad G. Khoshkholgh , Halim Yanikomeroglu

Offline reinforcement learning suffers from the out-of-distribution issue and extrapolation error. Most policy constraint methods regularize the density of the trained policy towards the behavior policy, which is too restrictive in most…

Machine Learning · Computer Science 2023-11-16 Yixiu Mao , Hongchang Zhang , Chen Chen , Yi Xu , Xiangyang Ji

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

Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many…

Machine Learning · Computer Science 2019-01-21 Dmitry Kangin , Nicolas Pugeault

Multi-step LLM agents in interactive environments represent a crucial step toward long-horizon decision-making. To train such agents, group-based reinforcement learning is widely adopted, which reinforces trajectories with higher relative…

Artificial Intelligence · Computer Science 2026-05-29 Jiazhen Yuan , Zhike Gong , Jinquan Hang , Zhengbiao Bai , Wei Zhao

Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates…

Machine Learning · Computer Science 2025-05-26 Ben Rahman

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). However, recent studies question whether RL genuinely expands reasoning…

Machine Learning · Computer Science 2026-02-04 Dayu Wang , Jiaye Yang , Weikang Li , Jiahui Liang , Yang Li

We explore Deep Reinforcement Learning in a parameterized action space. Specifically, we investigate how to achieve sample-efficient end-to-end training in these tasks. We propose a new compact architecture for the tasks where the parameter…

Machine Learning · Computer Science 2018-10-24 Ermo Wei , Drew Wicke , Sean Luke

Proximal policy optimization (PPO) approximates the trust region update using multiple epochs of clipped SGD. Each epoch may drift further from the natural gradient direction, creating path-dependent noise. To understand this drift, we can…

Machine Learning · Computer Science 2026-03-16 Zelal Su , Mustafaoglu , Sungyoung Lee , Eshan Balachandar , Risto Miikkulainen , Keshav Pingali

Grasping objects of different shapes and sizes - a foundational, effortless skill for humans - remains a challenging task in robotics. Although model-based approaches can predict stable grasp configurations for known object models, they…

Robotics · Computer Science 2022-11-22 Malte Mosbach , Sven Behnke

In many domains of empirical sciences, discovering the causal structure within variables remains an indispensable task. Recently, to tackle with unoriented edges or latent assumptions violation suffered by conventional methods, researchers…

Machine Learning · Computer Science 2024-12-30 Shixuan Liu , Yanghe Feng , Keyu Wu , Guangquan Cheng , Jincai Huang , Zhong Liu

On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Zhe Wu , Junliang Xing

In this paper, we tackle the challenging problem of delayed rewards in reinforcement learning (RL). While Proximal Policy Optimization (PPO) has emerged as a leading Policy Gradient method, its performance can degrade under delayed rewards.…

On-policy reinforcement learning (RL) has become a popular framework for solving sequential decision problems due to its computational efficiency and theoretical simplicity. Some on-policy methods guarantee every policy update is…

Machine Learning · Computer Science 2023-12-12 K. R. Zentner , Ujjwal Puri , Zhehui Huang , Gaurav S. Sukhatme

Despite the fact that offline methods for Large Language Models (LLMs) alignment do not require a direct reward model, they remain susceptible to overoptimization. This issue arises when the trained model deviates excessively from the…

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on new tasks or domains. Inspired by trust-region policy optimization (TRPO) and proximal policy…

Machine Learning · Computer Science 2026-04-14 Wenhong Zhu , Ruobing Xie , Rui Wang , Xingwu Sun , Di Wang , Pengfei Liu

Most of reinforcement learning algorithms optimize the discounted criterion which is beneficial to accelerate the convergence and reduce the variance of estimates. Although the discounted criterion is appropriate for certain tasks such as…

Machine Learning · Computer Science 2021-11-02 Xiaoteng Ma , Xiaohang Tang , Li Xia , Jun Yang , Qianchuan Zhao