A Survey Analyzing Generalization in Deep Reinforcement Learning.
Ezgi KorkmazPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- optimal policy
- model free
- optimal control
- markov decision processes
- machine learning
- deep learning
- temporal difference
- information retrieval
- real time
- dynamic programming
- unsupervised learning
- active learning
- transfer learning
- evolutionary algorithm
- learning process
- bayesian networks
- image sequences
- action selection
- reinforcement learning algorithms