paper-with-me

Papers

TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning

2024-11-28 · Batıkan Bora Ormancı, Phillip Swazinna, Steffen Udluft, Thomas A. Runkler

In this paper, we investigate offline reinforcement learning (RL) with the goal of training a single robust policy that generalizes effectively across environments with unseen dynamics. We propose a novel approach, Trajectory Encoding Augmentation (TEA), which extends the state space by integrating latent representations of environmental dynamics obtained from sequence encoders, such as AutoEncoders. Our findings show that incorporating these encodings with TEA improves the transferability of a single policy to novel environments with new dynamics, surpassing methods that rely solely on unmodified states. These results indicate that TEA captures critical, environment-specific characteristics, enabling RL agents to generalize effectively across dynamic conditions.

📄 PDF Abstract BibTeX arXiv:2411.19133

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Trajectory-Level Data Augmentation for Offline Reinforcement Learning

2026-05-13 · Tobias Schmähling, Matthias Burkhardt, Tobias Windisch arxiv

We propose a data augmentation method for offline reinforcement learning, motivated by active positioning problems. Particularly, our approach enables the training of off-policy models from a limited number of suboptimal…

Reinforcement LearningData Augmentation

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

ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts

2025-11-28 · Hang Yu, Di Zhang, Qiwei Du, Yanping Zhao 외 arxiv

Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented trajectories present challenges for reward propagation, res…

Reinforcement LearningData AugmentationOffline RL

Offline Trajectory Generalization for Offline Reinforcement Learning

2024-04-16 · Ziqi Zhao, Zhaochun Ren, Liu Yang, Fajie Yuan 외

Offline reinforcement learning (RL) aims to learn policies from static datasets of previously collected trajectories. Existing methods for offline RL either constrain the learned policy to the support of offline data or …

D4RLData AugmentationOffline RLreinforcement-learning+2

Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning

2023-04-10 · Junjie Zhang, Jiafei Lyu, Xiaoteng Ma, Jiangpeng Yan 외

Equipped with the trained environmental dynamics, model-based offline reinforcement learning (RL) algorithms can often successfully learn good policies from fixed-sized datasets, even some datasets with poor quality. Unf…

D4RLData AugmentationOffline RLreinforcement-learning+1