MushroomRL: Simplifying Reinforcement Learning Research.
Carlo D'EramoDavide TateoAndrea BonariniMarcello RestelliJan PetersPublished in: J. Mach. Learn. Res. (2021)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- multi agent
- control problems
- machine learning
- optimal control
- relational reinforcement learning
- evolutionary learning
- temporal difference
- optimal policy
- dynamic programming
- learning process
- search algorithm
- learning problems
- action selection
- temporal difference learning
- decision trees
- transition model
- information retrieval