paper-with-me

Papers

Augmenting Offline Reinforcement Learning with State-only Interactions

2024-02-01 · Shangzhe Li, Xinhua Zhang

Batch offline data have been shown considerably beneficial for reinforcement learning. Their benefit is further amplified by upsampling with generative models. In this paper, we consider a novel opportunity where interaction with environment is feasible, but only restricted to observations, i.e., \textit{no reward} feedback is available. This setting is broadly applicable, as simulators or even real cyber-physical systems are often accessible, while in contrast reward is often difficult or expensive to obtain. As a result, the learner must make good sense of the offline data to synthesize an efficient scheme of querying the transition of state. Our method first leverages online interactions to generate high-return trajectories via conditional diffusion models. They are then blended with the original offline trajectories through a stitching algorithm, and the resulting augmented data can be applied generically to downstream reinforcement learners. Superior empirical performance is demonstrated over state-of-the-art data augmentation methods that are extended to utilize state-only interactions.

📄 PDF Abstract BibTeX arXiv:2402.00807

Code (0)

등록된 구현이 없습니다.

Tasks

D4RLData AugmentationKnowledge Distillationreinforcement-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…
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis

2025-05-19 · Ruiquan Huang, Donghao Li, Chengshuai Shi, Cong Shen 외

This paper investigates a hybrid learning framework for reinforcement learning (RL) in which the agent can leverage both an offline dataset and online interactions to learn the optimal policy. We present a unified algori…

AllMulti-Armed BanditsReinforcement Learning (RL)

GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning

2024-05-27 · Jaewoo Lee, Sujin Yun, Taeyoung Yun, Jinkyoo Park

Offline Reinforcement Learning (Offline RL) presents challenges of learning effective decision-making policies from static datasets without any online interactions. Data augmentation techniques, such as noise injection a…

Data AugmentationDecision MakingOffline RLreinforcement-learning+1

DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning

2022-03-13 · ICLR 2022 4 · Jinxin Liu, Hongyin Zhang, Donglin Wang

Offline reinforcement learning algorithms promise to be applicable in settings where a fixed dataset is available and no new experience can be acquired. However, such formulation is inevitably offline-data-hungry and, in…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

SOReL and TOReL: Two Methods for Fully Offline Reinforcement Learning

2025-05-28 · Mattie Fellows, Clarisse Wibault, Uljad Berdica, Johannes Forkel 외

Sample efficiency remains a major obstacle for real world adoption of reinforcement learning (RL): success has been limited to settings where simulators provide access to essentially unlimited environment interactions, w…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Offline Reinforcement Learning with Fisher Divergence Critic Regularization

2021-03-14 · Ilya Kostrikov, Jonathan Tompson, Rob Fergus, Ofir Nachum

Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring divergence of the policy from the offline d…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)