Guiding Robot Exploration in Reinforcement Learning via Automated Planning
| Reinforcement Learning Automated Planning Robotics |
PaperID: 86
pdf
poster
|
| Reinforcement learning (RL) enables an agent to learn from trial-and-error experiences toward achieving long-term goals; automated planning aims to compute plans for accomplishing tasks using action knowledge. Despite their shared goal of completing complex tasks, the development of RL and automated planning has been largely isolated due to their different computational modalities. Focusing on improving RL agents' learning efficiency, we develop Guided Dyna-Q (GDQ) to enable RL agents to reason with action knowledge to avoid exploring less-relevant states. The action knowledge is used for generating artificial experiences from an optimistic simulation. GDQ has been evaluated in simulation and using a mobile robot conducting navigation tasks in a multi-room office environment. Compared with competitive baselines, GDQ significantly reduces the effort in exploration while improving the quality of learned policies. | |
Session 23: Reinforcement Learning
Guiding Robot Exploration in Reinforcement Learning via Automated Planning
Authors: Yohei Hayamizu, Saeid Amiri, Kishan Chandan, Keiki Takadama and Shiqi Zhang
Keywords:
Reinforcement LearningAutomated PlanningRobotics
A Simulator-based Planning Framework for Optimizing Autonomous Greenhouse Control Strategy
Authors: Zhicheng An, Xiaoyan Cao, Yao Yao, Wanpeng Zhang, Lanqing Li, Yue Wang, Shihui Guo and Dijun Luo
Keywords:
Simulator-based planningGreenhouse control strategyArtificial intelligenceReinforcement learningHeuristic algorithm
A Deep Ensemble Method for Multi-Agent Reinforcement Learning: A Case Study on Air Traffic Control
Authors: Supriyo Ghosh, Sean Laguna, Shiau Hong Lim, Laura Wynter and Hasan Poonawala
Keywords:
Reinforcement LearningDeep Ensemble LearningAir Traffic Control
Constrained Multiagent Markov Decision Processes: a Taxonomy of Problems and Algorithms
Authors: Frits de Nijs, Erwin Walraven, Mathijs De Weerdt and Matthijs T. J. Spaan