Style-Agnostic Reinforcement Learning.
Juyong LeeSeokjun AhnJaesik ParkPublished in: ECCV (39) (2022)
Keyphrases
- reinforcement learning
- model free
- state space
- function approximation
- optimal control
- optimal policy
- robotic control
- control problems
- reinforcement learning algorithms
- markov decision processes
- policy search
- multi agent
- knowledge base
- artificial intelligence
- learning capabilities
- reinforcement learning methods
- data sets
- evolutionary algorithm
- multi agent reinforcement learning
- continuous state
- stochastic approximation
- learning agents
- action space
- data mining
- temporal difference
- action selection
- support vector
- transfer learning