Automating Control of Overestimation Bias for Continuous Reinforcement Learning.
Arsenii KuznetsovAlexander GrishinArtem TsypinArsenii AshukhaDmitry P. VetrovPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- optimal control
- control problems
- robot control
- control system
- control method
- action space
- function approximation
- adaptive control
- process control
- control strategies
- database
- control theory
- feedback control
- control policy
- control policies
- robotic control
- reinforcement learning algorithms
- piecewise linear
- temporal difference
- markov decision processes
- transfer learning
- state space
- dynamic programming
- hidden markov models
- multi agent
- genetic algorithm
- neural network