Non-Parametric Policy Gradients: A Unified Treatment of Propositional and Relational Domains thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Non-Parametric Policy Gradients: A Unified Treatment of Propositional and Relational Domains

Published on Aug 04, 20083070 Views

Policy gradient approaches are a powerful instrument for learning how to interact with the environment.Existing approaches have focused on propositional and continuous domains only. Without extensive