Is High Variance Unavoidable in RL? A Case Study in Continuous Control.
Johan BjorckCarla P. GomesKilian Q. WeinbergerPublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- control problems
- control system
- control strategies
- wide range
- learning algorithm
- adaptive control
- test bed
- low variance
- control policy
- control theory
- action selection
- control strategy
- case study
- prediction error
- high precision
- state space
- trade off
- continuous domains
- multi agent
- objective function
- control policies
- machine learning