Evolving Reservoirs for Meta Reinforcement Learning.
Corentin LégerGautier HamonEleni NisiotiXavier HinautClément Moulin-FrierPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- meta level
- model free
- learning algorithm
- optimal policy
- reinforcement learning algorithms
- state space
- temporal difference
- supervised learning
- function approximators
- transfer learning
- learning process
- machine learning
- robotic control
- real time
- data sets
- action selection
- optimal control
- markov decision processes
- mobile robot
- action space
- dynamic programming
- autonomous learning
- multi agent reinforcement learning
- transition model
- real world