Reinforcement Learning using Guided Observability
Due to recent breakthroughs, reinforcement learning (RL) has demonstrated impressive performance in challenging sequential decision-making problems. However, an open question is how to make RL cope with partial observability which is prevalent in many real-world problems. Contrary to contemporary RL approaches, which focus mostly on improved memory representations or strong assumptions about the type of partial observability, we propose a simple but efficient approach that can be applied together with a wide variety of RL methods. Our main insight is that smoothly transitioning from full observability to partial observability during the training process yields a high performance policy. The approach, called partially observable guided reinforcement learning (PO-GRL), allows to utilize full state information during policy optimization without compromising the optimality of the final policy. A comprehensive evaluation in discrete partially observableMarkov decision process (POMDP) benchmark problems and continuous partially observable MuJoCo and OpenAI gym tasks shows that PO-GRL improves performance. Finally, we demonstrate PO-GRL in the ball-in-the-cup task on a real Barrett WAM robot under partial observability.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingMuJoCoOpenAI GymOpen-Ended Question Answeringreinforcement-learningReinforcement LearningReinforcement Learning (RL)Sequential Decision MakingSimilar Papers 제목 키워드 기반
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
Partial observability presents a significant challenge for Safe Reinforcement Learning (Safe RL), as it impedes the identification of potential risks and rewards. Leveraging specific types of privileged information durin…
Reinforcement LearningGuided Policy Optimization under Partial Observability
Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, such as that available in simulations, can …
continuous-controlContinuous ControlImitation LearningReinforcement Learning (RL)Reinforcement Learning under Partial Observability Guided by Learned Environment Models
In practical applications, we can rarely assume full observability of a system's environment, despite such knowledge being important for determining a reactive control system's precise interaction with its environment. T…
Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Multi-Agent Guided Policy Optimization
Due to practical constraints such as partial observability and limited communication, Centralized Training with Decentralized Execution (CTDE) has become the dominant paradigm in cooperative Multi-Agent Reinforcement Lea…
Multi-agent Reinforcement LearningActive Vision Reinforcement Learning under Limited Visual Observability
In this work, we investigate Active Vision Reinforcement Learning (ActiveVision-RL), where an embodied agent simultaneously learns action policy for the task while also controlling its visual observations in partially ob…
reinforcement-learningReinforcement Learning