Accelerating Human-Agent Collaborative Reinforcement Learning
View/ Open
Date
2021-07-02Author
Lygerakis, Fotios
Dagioglou, Maria
Karkaletsis, Vangelis
Metadata
Show full item recordAbstract
In domains such as Human-Robot Collaboration artificial agents
must be able to support mutual adaptation and learning. Towards
this direction, we use a discrete Soft Actor-Critic agent on a realtime collaborative game with humans. We examine how different
allocations of on-line and off-line gradient updates impact the game
performance and the total training time. Our results suggest that
early allocation of a high number of off-line g/u can accelerate
learning while shortening training duration.