Gradient Monitored Reinforcement Learning.
Mohammed Sharafath Abdul HameedGavneet Singh ChadhaAndreas SchwungSteven X. DingPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- policy gradient
- function approximation
- state space
- reinforcement learning algorithms
- optimal policy
- transfer learning
- optimal control
- steepest ascent
- policy search
- multi agent reinforcement learning
- gradient information
- temporal difference
- edge detection
- multi agent
- markov decision processes
- partially observable
- mobile robot
- temporal difference learning
- continuous state
- gradient direction
- real time
- model free
- least squares
- reinforcement learning methods
- multiscale
- case study
- robotic control
- learning algorithm