Automating Reinforcement Learning with Example-based Resets.
Jigang KimJae Hyeon ParkDaesol ChoH. Jin KimPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- evolutionary learning
- reinforcement learning algorithms
- markov decision processes
- control problems
- temporal difference
- model free
- robotic control
- learning algorithm
- machine learning
- relational reinforcement learning
- learning problems
- optimal policy
- learning process
- data mining
- dynamical systems
- transfer learning
- dynamic programming
- multi agent
- objective function
- partially observable
- decision trees
- robot control
- information systems
- multi agent reinforcement learning
- policy search
- computer vision
- direct policy search