Can Reinforcement Learning for Continuous Control Generalize Across Physics Engines?
Aaqib Parvez MohammedMatias Valdenegro-ToroPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- optimal control
- control problems
- control system
- artificial intelligence
- robot control
- action selection
- robotic control
- learning algorithm
- computer science
- learning process
- reinforcement learning algorithms
- function approximation
- control policy
- action space
- control theory
- autonomous robots
- real time
- markov decision processes
- optimal policy
- machine learning