Maximum Causal Entropy Inverse Constrained Reinforcement Learning.
Mattijs BaertPietro MazzagliaSam LerouxPieter SimoensPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- mutual information
- information theoretic
- bayesian networks
- maximum number
- temporal difference learning
- state space
- temporal difference
- reinforcement learning algorithms
- causal relationships
- causal reasoning
- multi agent
- robotic control
- information entropy
- causal models
- function approximators
- fuzzy entropy
- learning classifier systems
- markov decision processes
- dynamic programming
- learning process
- multi agent systems
- causal networks
- causal structure
- learning algorithm
- jacobian matrix
- genetic algorithm