新框架GATN提升强化学习跨域迁移的泛化与鲁棒性
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
- 通过无领域依赖表征+自适应策略适配器实现智能迁移
- 在Atari、MuJoCo等环境上表现优于基线，计算开销更低
- 适合需动态适应的真实场景，如聊天机器人和机器人控制
强化学习中的迁移学习使智能体能利用源任务知识加速目标任务学习。尽管先前工作如A2T框架解决了负迁移和选择性迁移问题，其他关键挑战仍待探索。本文提出广义自适应迁移网络（GATN），一种深度强化学习架构，旨在应对跨域泛化、环境变化鲁棒性及计算效率问题。GATN采用无领域依赖表示模块、鲁棒性感知策略适配器和高效迁移调度器实现上述目标。我们在Atari 2600、MuJoCo及自建聊天对话环境等多个基准上评估GATN，结果表明其在跨域泛化、动态环境适应性和计算开销方面均优于基线方法。研究显示GATN是实际强化学习应用（如自适应聊天机器人和机器人控制）的通用框架。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。