From Semantics to Execution: Integrating Action Planning With Reinforcement Learning for Robotic Causal Problem-Solving
Reinforcement learning is generally accepted to be an appropriate and successful method to learn robot control. Symbolic action planning is useful to resolve causal dependencies and to break a causally complex problem down into a sequence of simpler high-level actions. A problem with the integration...
Main Authors: | Manfred Eppe, Phuong D. H. Nguyen, Stefan Wermter |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2019-11-01
|
Series: | Frontiers in Robotics and AI |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/frobt.2019.00123/full |
Similar Items
-
How to Solve the Torus Puzzle
by: Masahiro Nakamura, et al.
Published: (2012-01-01) -
The Path Planning of Mobile Robot by Neural Networks and Hierarchical Reinforcement Learning
by: Jinglun Yu, et al.
Published: (2020-10-01) -
Robotic Cuber : A Rubik´s Cube solving robot
by: GRÖNÅS, DANIEL, et al.
Published: (2020) -
Incorporating causal factors into reinforcement learning for dynamic treatment regimes in HIV
by: Chao Yu, et al.
Published: (2019-04-01) -
The Rooftop Raven Project: An Exploratory, Qualitative Study of Puzzle Solving Ability in Wild and Captive Ravens
by: Cory, Emily Faun
Published: (2016)