On First-Order Meta-Reinforcement Learning with Moreau Envelopes.
Mohammad Taha ToghaniSebastian Perez-SalazarCésar A. UribePublished in: CDC (2023)
Keyphrases
- markov decision process
- reinforcement learning
- state space
- markov decision processes
- optimal policy
- first order logic
- higher order
- function approximation
- learning algorithm
- multi agent
- temporal difference
- meta level
- reinforcement learning algorithms
- inductive logic programming systems
- stochastic dominance
- action space
- model free
- expert systems
- machine learning
- universally quantified
- data mining