Skill-based curiosity for intrinsically motivated reinforcement learning.
Nicolas BougieRyutaro IchisePublished in: Mach. Learn. (2020)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference learning
- optimal policy
- reinforcement learning algorithms
- model free
- state space
- multi agent
- robotic control
- optimal control
- learning algorithm
- machine learning
- behavioural cloning
- learning classifier systems
- multi agent reinforcement learning
- stochastic approximation
- markov decision process
- control problems
- temporal difference
- action selection
- database
- markov decision processes
- artificial intelligence
- databases