Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss.
Michael L. IuzzolinoMichael C. MozerSamy BengioPublished in: NeurIPS (2021)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- td learning
- evaluation function
- monte carlo
- step size
- model free
- action selection
- temporal difference learning
- reinforcement learning algorithms
- policy evaluation
- temporal difference methods
- genetic algorithm
- objective function
- learning tasks
- text categorization
- multi objective
- policy iteration