Optimizing thermodynamic trajectories using evolutionary reinforcement learning.
Chris BeelerUladzimir YahorauRory ColesKyle MillsStephen WhitelamIsaac TamblynPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- genetic algorithm
- reinforcement learning algorithms
- evolutionary computation
- moving objects
- evolutionary optimization
- state space
- trajectory data
- optimal policy
- dynamic programming
- model free
- temporal difference
- experimental data
- multi agent
- trajectories of moving objects
- machine learning
- multi agent reinforcement learning
- action selection
- robotic control
- markov decision processes
- learning process
- spatio temporal
- transfer learning
- genetic programming
- supervised learning
- phase space
- evolutionary methods
- location prediction
- learning algorithm
- neural network