Off-Policy Meta-Reinforcement Learning With Belief-Based Task Inference

Off-Policy Meta-Reinforcement Learning With Belief-Based Task Inference

Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for solving a new task. However, most existing meta-RL methods require partially or fully on-policy data, which hinders the improvement of sample efficiency. To allevia...

Full description

Bibliographic Details
Main Authors: Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Artificial intelligence
inference
meta learning
reinforcement learning
uncertainty
Online Access:https://ieeexplore.ieee.org/document/9763505/

Internet

https://ieeexplore.ieee.org/document/9763505/

Similar Items