paper-with-me

Papers

Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay

2024-04-16 · Jinmei Liu, Wenbin Li, Xiangyu Yue, Shilin Zhang, Chunlin Chen, Zhi Wang

We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains previous knowledge by concurrent replay of generated pseudo-data. First, we decouple the continual learning policy into a diffusion-based generative behavior model and a multi-head action evaluation model, allowing the policy to inherit distributional expressivity for encompassing a progressive range of diverse behaviors. Second, we train a task-conditioned diffusion model to mimic state distributions of past tasks. Generated states are paired with corresponding responses from the behavior generator to represent old tasks with high-fidelity replayed samples. Finally, by interleaving pseudo samples with real ones of the new task, we continually update the state and behavior generators to model progressively diverse behaviors, and regularize the multi-head critic via behavior cloning to mitigate forgetting. Experiments demonstrate that our method achieves better forward transfer with less forgetting, and closely approximates the results of using previous ground-truth data due to its high-fidelity replay of the sample space. Our code is available at \href{https://github.com/NJU-RL/CuGRO}{https://github.com/NJU-RL/CuGRO}.

📄 PDF Abstract BibTeX arXiv:2404.10662

Code (1)

nju-rl/cugro 공식 구현 pytorch

Tasks

Continual Learningreinforcement-learningReinforcement Learning

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

Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal

2024-09-04 · Jifeng Hu, Li Shen, Sili Huang, Zhejian Yang 외

Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static. However, in real-world ap…

Reinforcement Learning (RL)

Offline Reinforcement Learning with Generative Trajectory Policies

2025-10-13 · Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen arxiv

Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slo…

Reinforcement LearningOffline RL

Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning

2026-05-29 · Ha Manh Bui, Metod Jazbec, Eric Nalisnick, Anqi Liu arxiv

Offline-to-Online Reinforcement Learning (O2O-RL) leverages an offline, pre-trained policy to minimize costly online interactions. Although data-efficient, O2O-RL is susceptible to shifts between offline and online distr…

Reinforcement Learning

Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning

2023-09-29 · Zihan Ding, Chi Jin

Score-based generative models like the diffusion model have been testified to be effective in modeling multi-modal data from image generation to reinforcement learning (RL). However, the inference process of diffusion mo…

Image GenerationOffline RLReinforcement Learning (RL)

DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning

2024-06-13 · Xuemin Hu, Shen Li, Yingfen Xu, Bo Tang 외

Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent cannot often cover the action distribution…

D4RLOffline RLreinforcement-learningReinforcement Learning+1