Explicitly Encouraging Low Fractional Dimensional Trajectories Via Reinforcement Learning.
Sean GillenKatie BylPublished in: CoRL (2020)
Keyphrases
- reinforcement learning
- multi dimensional
- high levels
- function approximation
- hurst exponent
- learning algorithm
- state space
- configuration space
- data mining
- reinforcement learning algorithms
- markov decision processes
- robotic control
- temporal difference
- optimal control
- optimal policy
- dynamic programming
- machine learning