arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2004.00048cs.AI
收藏

用强化学习模拟进化

Mimicking Evolution with Reinforcement Learning

Instituto Superior de Engenharia de Lisboa(里斯本高等工程学院);Delft University of Technology(代尔夫特理工大学)

João P. Abrantes, Arnaldo J. Abrantes, Frans A. Oliehoek

摘要:

进化在地球上产生了人类和动物的智慧。我们认为,发展人工类人智能的道路将通过在类似自然的模拟中模仿进化过程。在自然界中,有两个过程驱动着大脑的发展:进化和学习。进化是缓慢的,跨越几代人,除其他外,它通过改变其内部奖励功能来定义代理人学习的内容。学习在一个人的一生中迅速发挥作用,它迅速更新代理人的政策,以最大限度地提高快乐,最小化痛苦。通过进化,奖励函数慢慢地与适应度函数一致,然而,随着代理的进化,环境及其适应度函数也发生变化,增加了奖励和适应度之间的不一致。在模拟中复制这两个过程在计算上是极其昂贵的。这项工作提出了通过进化奖励(EvER)的进化,通过确保奖励函数与适应度函数的一致性,允许学习独自驱动搜索具有越来越多的进化适应度的策略。在这个搜索中,EvER利用了代理在其生命周期中经历的整个状态-动作轨迹。相比之下,目前的进化算法丢弃这些信息,从而限制了它们在处理顺序决策问题时的潜在效率。我们在两个简单的生物启发的环境中测试我们的算法,并显示其优越性,在生成更有能力的代理人在生存和繁殖他们的基因相比,一个国家的最先进的进化算法。

英文摘要:

Evolution gave rise to human and animal intelligence here on Earth. We argue that the path to developing artificial human-like-intelligence will pass through mimicking the evolutionary process in a nature-like simulation. In Nature, there are two processes driving the development of the brain: evolution and learning. Evolution acts slowly, across generations, and amongst other things, it defines what agents learn by changing their internal reward function. Learning acts fast, across one's lifetime, and it quickly updates agents' policy to maximise pleasure and minimise pain. The reward function is slowly aligned with the fitness function by evolution, however, as agents evolve the environment and its fitness function also change, increasing the misalignment between reward and fitness. It is extremely computationally expensive to replicate these two processes in simulation. This work proposes Evolution via Evolutionary Reward (EvER) that allows learning to single-handedly drive the search for policies with increasingly evolutionary fitness by ensuring the alignment of the reward function with the fitness function. In this search, EvER makes use of the whole state-action trajectories that agents go through their lifetime. In contrast, current evolutionary algorithms discard this information and consequently limit their potential efficiency at tackling sequential decision problems. We test our algorithm in two simple bio-inspired environments and show its superiority at generating more capable agents at surviving and reproducing their genes when compared with a state-of-the-art evolutionary algorithm.

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。

↑