TEA：用于离线强化学习中鲁棒且可迁移策略的轨迹编码增强
TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning
AI总结：
本文提出轨迹编码增强（TEA）方法，通过整合序列编码器提取的动态潜在表示来扩展状态空间，有效提升了离线强化学习中单一策略在未见动态环境下的鲁棒性与可迁移性。
摘要：
在本文中，我们研究了离线强化学习（RL），目标是训练单一鲁棒策略，使其能在具有未见动态的环境中有效泛化。我们提出了一种新方法，轨迹编码增强（TEA），该方法通过整合从序列编码器（如AutoEncoders）获得的动态潜在表示来扩展状态空间。研究结果表明，利用TEA整合这些编码提升了单一策略向具有新动态的新环境的可迁移性，超越了仅依赖未修改状态的方法。这些结果表明TEA捕获了关键的环境特定特征，使RL智能体能在动态条件下有效泛化。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
