Self-Paced Deep Reinforcement Learning.
Pascal KlinkCarlo D'EramoJan PetersJoni PajarinenPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- function approximation
- optimal policy
- temporal difference
- markov decision processes
- direct policy search
- reinforcement learning algorithms
- model free
- state space
- learning algorithm
- multi agent
- control problems
- machine learning
- temporal difference learning
- multi agent reinforcement learning
- data sets
- supervised learning
- active learning
- database
- learning problems
- learning process
- action space
- stochastic approximation