Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning.
Md. Masudur RahmanYexiang XuePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal policy
- transfer learning
- machine learning
- multi agent
- policy search
- action selection
- optimization problems
- reinforcement learning algorithms
- markov decision process
- function approximation
- robust optimization
- optimization algorithm
- learning algorithm
- global optimization
- temporal difference
- markov decision processes
- state space
- supervised learning
- policy evaluation
- reinforcement learning problems
- neural network
- computationally efficient
- sufficient conditions
- function approximators
- state and action spaces