对抗式强化学习：为高效和可扩展的深度强化学习重新思考核心原理
Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning
AI总结：
本文提出基于对抗性行动经验的理论新范式，解决高维MDP中状态空间爆炸导致的计算复杂性与策略成功率矛盾，通过实验验证方法在高维环境中的高效性和样本效率。
摘要：
在通过与环境交互无需监督即可赢得任务的学习策略成功后，智能体获得了在复杂MDP中进行序列决策的能力。然而，强化学习策略在高维MDP中面临指数级增长的状态空间，导致计算复杂性与策略成功率之间的二元对立。本文聚焦于学习阶段中智能体在高维MDP中与环境的交互，引入基于对抗性行动经验的理论新范式。我们的分析和方法为高效、有效、可扩展和加速学习提供了理论基础，并在不增加额外计算复杂性的同时，显著加快了训练速度。我们在Arcade Learning Environment中进行了广泛的实验，涉及高维状态表示的MDP。实验结果进一步验证了我们的理论分析，我们的方法在高维环境中实现了显著的性能提升，并具有实质性的样本效率。
英文摘要：
Following the pivotal success of learning strategies to win at tasks, solely by interacting with an environment without any supervision, agents have gained the ability to make sequential decisions in complex MDPs. Yet, reinforcement learning policies face exponentially growing state spaces in high dimensional MDPs resulting in a dichotomy between computational complexity and policy success. In our paper we focus on the agent's interaction with the environment in a high-dimensional MDP during the learning phase and we introduce a theoretically-founded novel paradigm based on experiences obtained through counteractive actions. Our analysis and method provide a theoretical basis for efficient, effective, scalable and accelerated learning, and further comes with zero additional computational complexity while leading to significant acceleration in training. We conduct extensive experiments in the Arcade Learning Environment with high-dimensional state representation MDPs. The experimental results further verify our theoretical analysis, and our method achieves significant performance increase with substantial sample-efficiency in high-dimensional environments.
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。
