Stochastic Halpern iteration in normed spaces and applications to reinforcement learning.
Mario BravoJuan Pablo ContrerasPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- direct policy search
- stochastic approximation
- learning automata
- control policies
- learning algorithm
- temporal difference
- continuous state spaces
- transfer learning
- vector space
- temporal logic
- causal models
- robotic control
- stochastic nature
- control problems
- model free
- function approximation
- monte carlo
- optimal policy
- learning process
- data sets
- stochastic processes
- graph matching
- function approximators
- modal logic
- multi agent reinforcement learning
- state space
- multi agent
- model free reinforcement learning