Delayed Geometric Discounts: An Alternative Criterion for Reinforcement Learning.
Firas JarbouiAhmed AkakziaPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- optimization criterion
- dynamic programming
- learning environment
- geometric constraints
- temporal difference
- reinforcement learning algorithms
- geometric transformations
- temporal difference learning
- state space
- learning tasks
- learning problems
- geometric structure
- multiple criteria
- model free
- geometric information
- markov decision process
- multi agent