Automating Staged Rollout with Reinforcement Learning.
Shadow PritchardVidhyashree NagarajuLance FiondellaPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- state space
- model free
- approximate policy iteration
- multi agent reinforcement learning
- reinforcement learning algorithms
- function approximation
- optimal policy
- robotic control
- neural network
- multi agent
- markov decision processes
- machine learning
- learning algorithm
- markov decision process
- control problems
- robot control
- learning classifier systems
- policy iteration
- stochastic approximation
- optimal control
- monte carlo tree search
- policy search
- relational reinforcement learning
- learning process
- learning problems