超级会员免费看
本文研究了在连续控制任务中不同环境的转移学习，指出政策转移的局限性，并提出了一种基于模型的价值中心（MVC）框架。MVC在源域中同时学习动态和价值近似器，以提高在新环境中的适应性。实验表明，MVC在从头开始训练时表现与基线相当，但在转移学习中显著超越了它们。
TRANSFER VALUE OR POLICY? A AVALUE-CENTRIC FRAMEWORK TOWARDS TRANSFERRABLE CONTINUOUS REINFORCEMENT LEARNING
ABSTRACT
Transferring learned knowledge from one environment to another is an important step towards practical reinforcement learning (RL). In this paper, we investigate the problem of transfer learning across environments with different dynamics while accomplishing the same task in the continuous control domain. We start by illustrating the limitations of policy-centric methods (policy gradient, actor-critic, etc.) when transferring knowledge across environments. We then propose a general model-based value-centric
订阅专栏 解锁全文
扫一扫
1539
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
