Quantifying Generalization in Reinforcement Learning.
Karl CobbeOleg KlimovChristopher HesseTaehoon KimJohn SchulmanPublished in: ICML (2019)
Keyphrases
- reinforcement learning
- function approximation
- model free
- learning algorithm
- markov decision processes
- state space
- temporal difference
- reinforcement learning algorithms
- optimal control
- transfer learning
- control problems
- multi agent
- database
- learning capabilities
- markov decision process
- autonomous learning
- relational reinforcement learning
- robotic control
- learning machines
- optimal policy
- dynamic programming
- learning process
- knowledge base
- neural network
- databases