CoachNet: An Adversarial Sampling Approach for Reinforcement Learning.
Elmira Amirloo AbolfathiJun LuoPeyman YadmellatKasra RezaeePublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent
- random sampling
- learning algorithm
- function approximation
- transfer learning
- sampling strategy
- sampling algorithm
- optimal policy
- machine learning
- reinforcement learning algorithms
- model free
- monte carlo
- learning process
- information retrieval
- supervised learning
- markov decision processes
- state space
- temporal difference
- robotic control
- dynamic programming
- markov chain monte carlo
- genetic algorithm
- robot control
- neural network
- reinforcement learning methods