Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning.
Finn RietzStefan HeinrichErik SchaffernichtJohannes Andreas StorkPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- learning algorithm
- decomposition algorithm
- decomposition method
- optimal policy
- dynamic programming
- temporal difference
- multi agent
- possibilistic logic
- machine learning
- decomposition methods
- image decomposition
- learning process
- reinforcement learning algorithms
- policy search
- temporal difference learning
- robotic control
- multi agent reinforcement learning
- reinforcement learning methods
- hard constraints
- markov decision process
- robot control
- markov decision processes