Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning.
Sahil SharmaGirish Raguvir JSrivatsan RameshBalaraman RavindranPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- online learning
- state space
- supervised learning
- learning mechanism
- post processing
- learning agents
- inductive inference
- mobile learning
- learning problems
- function approximation
- unsupervised learning
- temporal difference
- learning activities
- reinforcement learning algorithms
- dynamic programming
- temporal difference learning