Convex Q Learning in a Stochastic Environment: Extended Version.
Fan LuSean P. MeynPublished in: CoRR (2023)
Keyphrases
- stochastic approximation
- mobile robot
- reinforcement learning
- state space
- data sets
- dynamic environments
- real time
- cooperative
- multi agent
- markov random field
- genetic algorithm
- monte carlo
- computing environments
- potential field
- reinforcement learning algorithms
- model free
- robotic systems
- convex optimization
- evaluation function
- convergence rate
- virtual world
- control system