Programmatically Interpretable Reinforcement Learning.
Abhinav VermaVijayaraghavan MuraliRishabh SinghPushmeet KohliSwarat ChaudhuriPublished in: ICML (2018)
Keyphrases
- reinforcement learning
- state space
- reinforcement learning algorithms
- temporal difference
- learning algorithm
- multi agent
- markov decision processes
- function approximation
- model free
- robotic control
- optimal policy
- learning process
- control problems
- temporal difference learning
- reinforcement learning methods
- classification rules
- databases
- dynamic environments
- stochastic approximation
- relational reinforcement learning
- perceptual aliasing
- direct policy search