Curriculum goal masking for continuous deep reinforcement learning.
Manfred EppeSven MaggStefan WermterPublished in: ICDL-EPIROB (2019)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- learning algorithm
- action space
- state space
- professional development
- continuous state spaces
- temporal difference
- continuous domains
- fitted q iteration
- robotic control
- multi agent reinforcement learning
- temporal difference learning
- model free
- cooperative learning
- learning problems
- markov decision processes