Benchmarking Deep Reinforcement Learning for Continuous Control.
Yan DuanXi ChenRein HouthooftJohn SchulmanPieter AbbeelPublished in: ICML (2016)
Keyphrases
- reinforcement learning
- control problems
- adaptive control
- optimal control
- control method
- robot control
- function approximation
- control policy
- dynamic programming
- state space
- real time
- mobile robot
- control system
- process control
- continuous domains
- learning algorithm
- machine learning
- action space
- data mining
- least squares