arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.09243cs.ROcs.AIcs.LG
收藏

高效稳定的多步稀疏奖励强化学习的抽象演示与自适应探索

Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning

Cardiff University(卡迪夫大学)

Xintong Yang, Ze Ji, Jing Wu, Yu-kun Lai

摘要:

尽管深度强化学习(DRL)在包括机器人在内的许多学科中都很流行,但最先进的DRL算法仍然难以学习长时间、多步骤和稀疏奖励任务,例如仅在任务完成奖励信号的情况下堆叠几个块。为了提高这些任务的学习效率,本文提出了一种DRL探索技术,称为A^2,它集成了两个组件的灵感来自人类的经验:抽象演示和自适应探索。A^2首先将复杂任务分解为子任务,然后提供子任务的正确顺序来学习。在训练过程中,智能体自适应地探索环境,对掌握得好的子任务更确定地采取行动,对学得不好的子任务更随机。消融和比较实验进行了几个网格世界的任务和三个机器人操作任务。我们证明了A^2可以帮助流行的DRL算法(DQN,DDPG和SAC)在这些环境中更有效,更稳定地学习。

英文摘要:

Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks given only a task-completion reward signal. To improve learning efficiency for such tasks, this paper proposes a DRL exploration technique, termed A^2, which integrates two components inspired by human experiences: Abstract demonstrations and Adaptive exploration. A^2 starts by decomposing a complex task into subtasks, and then provides the correct orders of subtasks to learn. During training, the agent explores the environment adaptively, acting more deterministically for well-mastered subtasks and more stochastically for ill-learnt subtasks. Ablation and comparative experiments are conducted on several grid-world tasks and three robotic manipulation tasks. We demonstrate that A^2 can aid popular DRL algorithms (DQN, DDPG, and SAC) to learn more efficiently and stably in these 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。

↑