Benchmarking Deep Reinforcement Learning for Continuous Control.
Yan DuanXi ChenRein HouthooftJohn SchulmanPieter AbbeelPublished in: CoRR (2016)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- control policy
- robot control
- action space
- data sets
- control strategy
- continuous state spaces
- control strategies
- control method
- markov decision processes
- neural network
- function approximation
- piecewise linear
- model free
- adaptive control
- continuous domains
- control system
- multi agent systems
- multi agent
- temporal difference learning
- real time