Abstract
Transfer learning in Reinforcement Learning (RL) enables agents to leverage knowledge from source tasks to accelerate learning in target tasks. While prior work, such as the Attend, Adapt, and Transfer (A2T) framework, addresses negative transfer and selective transfer, other critical challenges remain underexplored. This paper introduces the Generalized Adaptive Transfer Network (GATN), a deep RL architecture designed to tackle task generalization across domains, robustness to environmental changes, and computational efficiency in transfer. GATN employs a domain-agnostic representation module, a robustness-aware policy adapter, and an efficient transfer scheduler to achieve these goals. We evaluate GATN on diverse benchmarks, including Atari 2600, MuJoCo, and a custom chatbot dialogue environment, demonstrating superior performance in cross-domain generalization, resilience to dynamic environments, and reduced computational overhead compared to baselines. Our findings suggest GATN is a versatile framework for real-world RL applications, such as adaptive chatbots and robotic control.
Abstract (translated)
在强化学习（RL）中，迁移学习使智能体能够利用来自源任务的知识来加速目标任务的学习过程。尽管之前的工作，如“Attend, Adapt, and Transfer”(A2T) 框架已经解决了负向迁移和选择性迁移的问题，但其他关键挑战仍然没有得到充分探索。本文介绍了广义自适应传输网络（GATN），这是一种深度强化学习架构，旨在解决跨领域任务泛化、对环境变化的鲁棒性和迁移过程中的计算效率等问题。 GATN采用了一个域无关表示模块，一个感知鲁棒性的策略适配器以及一个高效的转移调度程序来实现这些目标。我们在包括Atari 2600游戏、MuJoCo物理模拟器和一个自定义聊天机器人对话环境在内的多种基准测试中评估了GATN的性能，结果显示它在跨域泛化能力、对动态环境的适应能力和计算开销方面都优于基线方法。 我们的研究结果表明，GATN是一个适合现实世界强化学习应用（如自适应聊天机器人和机器人控制）的多功能框架。
URL
https://arxiv.org/abs/2507.03026
