Self-Paced Deep Reinforcement Learning.
Pascal KlinkCarlo D'EramoJan PetersJoni PajarinenPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- partially observable
- machine learning
- optimal policy
- markov decision processes
- direct policy search
- temporal difference
- brain computer interface
- multi agent reinforcement learning
- robotic control
- autonomous learning
- learning path
- transition model
- relational reinforcement learning
- action selection
- learning agents
- action space
- control problems
- model free
- online course
- semi supervised
- dynamic programming
- learning process
- multi agent
- image processing