Constrained Meta Agnostic Reinforcement Learning.
Karam DaaboulFlorian KuhmTim JosephJ. Marius ZoellnerPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- meta level
- function approximation
- reinforcement learning algorithms
- markov decision processes
- optimal policy
- model free
- learning algorithm
- meta reasoning
- learning process
- relational reinforcement learning
- information retrieval
- neural network
- database
- policy gradient
- autonomous learning
- high level abstraction
- optimal control
- learning tasks
- programming language
- semi supervised
- state space
- optimal solution
- real world
- data sets