paper-with-me

Papers

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning

2024-05-29 · Tianle Zhang, Jiayi Guan, Lin Zhao, Yihang Li, Dongjiang Li, Zecui Zeng, Lei Sun, Yue Chen, Xuelong Wei, Lusong Li, Xiaodong He

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for offline RL issues. However, previous offline RL algorithms based on diffusion policies generally adopt weighted regression to improve the policy. This approach optimizes the policy only using the collected actions and is sensitive to Q-values, which limits the potential for further performance enhancement. To this end, we propose a novel preferred-action-optimized diffusion policy for offline RL. In particular, an expressive conditional diffusion model is utilized to represent the diverse distribution of a behavior policy. Meanwhile, based on the diffusion model, preferred actions within the same behavior distribution are automatically generated through the critic function. Moreover, an anti-noise preference optimization is designed to achieve policy improvement by using the preferred actions, which can adapt to noise-preferred actions for stable training. Extensive experiments demonstrate that the proposed method provides competitive or superior performance compared to previous state-of-the-art offline RL methods, particularly in sparse reward tasks such as Kitchen and AntMaze. Additionally, we empirically prove the effectiveness of anti-noise preference optimization.

📄 PDF Abstract BibTeX arXiv:2405.18729

Code (0)

등록된 구현이 없습니다.

Tasks

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone

2024-12-09 · Max Sobol Mark, Tian Gao, Georgia Gabriela Sampaio, Mohan Kumar Srirama 외

Recent advances in learning decision-making policies can largely be attributed to training expressive policy models, largely via imitation learning. While imitation learning discards non-expert data, reinforcement learni…

global-optimizationImitation LearningOffline RLReinforcement Learning (RL)+1

Prior-Guided Diffusion Planning for Offline Reinforcement Learning

2025-05-16 · Donghyeon Ki, JunHyeok Oh, Seong-Woong Shim, Byung-Jun Lee

Diffusion models have recently gained prominence in offline reinforcement learning due to their ability to effectively learn high-performing, generalizable policies from static datasets. Diffusion-based planners facilita…

Decision MakingDenoisingOffline RLreinforcement-learning+1

Dichotomous Diffusion Policy Optimization

2025-12-31 · Ruiming Liang, Yinan Zheng, Kexin Zheng, Tianyi Tan 외 arxiv

Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference. However, effectively training la…

Reinforcement LearningAutonomous Driving

RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation

2026-08-20 · Shaoxuan Wang, Guangting Zheng, Rui Huang, Zhipeng Tang 외 arxiv

Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction. Yet prevalent diffusion- and flow-matching robot policies lack tractable likelihoods, limi…

Reinforcement LearningOffline RL

OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories

2026-02-11 · Returaj Burnwal, Nirav Pravinbhai Bhatt, Balaraman Ravindran arxiv

This work addresses the problem of offline safe imitation learning (IL), where the goal is to learn safe and reward-maximizing policies from demonstrations that do not have per-timestep safety cost or reward information.…