Challenging Common Assumptions in Convex Reinforcement Learning.
Mirco MuttiRiccardo De SantiPiersilvio De BartolomeisMarcello RestelliPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- piecewise linear
- convex optimization
- real world
- neural network
- robotic control
- temporal difference
- model free
- optimal policy
- state space
- machine learning
- markov decision processes
- evolutionary algorithm
- temporal difference learning
- simplifying assumptions
- real time