Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning.
Phillip SwazinnaSteffen UdluftDaniel HeinThomas A. RunklerPublished in: CoRR (2022)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- policy iteration
- function approximation
- rl algorithms
- temporal difference
- reinforcement learning methods
- policy evaluation
- learning algorithm
- state space
- impedance control
- machine learning
- markov decision processes
- machine learning algorithms
- supervised learning
- recommender systems
- average reward
- temporal difference learning
- feature vectors
- multi agent
- data mining