Reinforcement Learning with Non-Exponential Discounting.
Matthias SchultheisConstantin A. RothkopfHeinz KoepplPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- multi agent reinforcement learning
- learning algorithm
- control problems
- learning process
- learning problems
- markov decision processes
- robotic control
- reinforcement learning algorithms
- model free
- optimal policy
- multi agent
- genetic algorithm
- machine learning
- real time
- supervised learning
- optimal control
- social networks
- artificial intelligence
- reinforcement learning methods
- stochastic approximation
- active exploration