While reinforcement learning (RL) provides a framework for learning through trial and error, translating RL algorithms into the real world has remained challenging. A major hurdle to real-world application arises from the development of algorithms in an episodic setting where the environment is reset after every trial, in contrast with the continual and non-episodic nature of the real-world encountered by embodied agents such as humans and robots. Prior works have considered an alternating approach where a forward policy learns to solve the task and the backward policy learns to reset the environment, but what initial state distribution should the backward policy reset the agent to? Assuming access to a few demonstrations, we propose a new method, MEDAL, that trains the backward policy to match the state distribution in the provided demonstrations. This keeps the agent close to the task-relevant states, allowing for a mix of easy and difficult starting states for the forward policy. Our experiments show that MEDAL matches or outperforms prior methods on three sparse-reward continuous control tasks from the EARL benchmark, with 40% gains on the hardest task, while making fewer assumptions than prior works.
翻译:虽然强化学习(RL)为通过试验和错误学习提供了一个框架,但将RL算法转化为现实世界仍然具有挑战性。 现实世界应用的一个主要障碍来自在每次试验后环境被重新设置的偶发环境中发展算法,与人类和机器人等体现的代理人所遭遇的现实世界的持续和非偶然性质形成对比。 先前的工程考虑了一种交替方法,即先期政策学会解决任务,后期政策学会重新设置环境,但后期政策应该重新设定代理人的最初状态分布是什么? 假设可以使用一些演示,我们提出一种新的方法,即MEDAL,用来培训后期政策以匹配所提供的演示中的国家分布。 这使得代理人接近任务相关状态,从而可以混合各种容易和困难的起始状态来实施前期政策。 我们的实验表明,MEDAL匹配或超越了前三次从 EARL 基准中确定的三个微弱的连续控制任务,在最困难的任务上取得了40%的收益,同时作出比以前少的假设。