A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning.
Andrew PattersonAdam WhiteMartha WhitePublished in: J. Mach. Learn. Res. (2022)
Keyphrases
- reinforcement learning
- estimation error
- error analysis
- error rate
- estimation algorithm
- multi agent
- reinforcement learning algorithms
- error bounds
- function approximation
- error estimation
- estimation accuracy
- markov decision processes
- learning algorithm
- learning problems
- learning process
- error estimates
- robotic control