arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.02790cs.LGcs.AI
收藏

强化学习的学习合成环境和奖励网络

Learning Synthetic Environments and Reward Networks for Reinforcement Learning

University of Freiburg(弗莱堡大学);Bosch Center for Artificial Intelligence(博世人工智能中心)

Fabio Ferreira, Thomas Nierhoff, Andreas Saelinger, Frank Hutter

摘要:

我们引入合成环境(SE)和奖励网络(RN),神经网络表示,作为代理环境模型训练强化学习(RL)代理。我们表明,一个代理,专门在SE上训练后,能够解决相应的真实环境。虽然SE通过学习其状态动态和奖励来充当真实环境的完全代理,但RN是学习增强或替换奖励的部分代理。我们使用双层优化来进化SE和RN:内环训练RL代理,外环通过演化策略训练SE / RN的参数。我们评估我们提出的新概念广泛的RL算法和经典的控制环境。在一对一的比较中,学习SE代理需要与真实环境进行更多的交互,而不是只在真实环境中训练代理。然而,一旦学习了这样的SE,我们就不需要与真实环境进行任何交互来训练新的代理。此外,学习的SE代理允许我们训练代理与较少的互动,同时保持原有的任务性能。我们的实证研究结果表明,SE实现这一结果,通过学习知情的陈述,偏向代理商对相关国家。此外,我们发现,这些代理是强大的超参数变化,也可以转移到看不见的代理。

英文摘要:

We introduce Synthetic Environments (SEs) and Reward Networks (RNs), represented by neural networks, as proxy environment models for training Reinforcement Learning (RL) agents. We show that an agent, after being trained exclusively on the SE, is able to solve the corresponding real environment. While an SE acts as a full proxy to a real environment by learning about its state dynamics and rewards, an RN is a partial proxy that learns to augment or replace rewards. We use bi-level optimization to evolve SEs and RNs: the inner loop trains the RL agent, and the outer loop trains the parameters of the SE / RN via an evolution strategy. We evaluate our proposed new concept on a broad range of RL algorithms and classic control environments. In a one-to-one comparison, learning an SE proxy requires more interactions with the real environment than training agents only on the real environment. However, once such an SE has been learned, we do not need any interactions with the real environment to train new agents. Moreover, the learned SE proxies allow us to train agents with fewer interactions while maintaining the original task performance. Our empirical results suggest that SEs achieve this result by learning informed representations that bias the agents towards relevant states. Moreover, we find that these proxies are robust against hyperparameter variation and can also transfer to unseen agents.

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。

↑