Loss Dynamics of Temporal Difference Reinforcement Learning.
Blake BordelonPaul MassetHenry KuoCengiz PehlevanPublished in: NeurIPS (2023)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- td learning
- evaluation function
- model free
- temporal difference learning
- reinforcement learning algorithms
- policy evaluation
- monte carlo
- actor critic
- temporal difference methods
- function approximators
- step size
- dynamical systems
- action selection
- policy iteration
- state space
- supervised learning
- learning algorithm
- optimal policy
- evolutionary algorithm
- policy search
- reinforcement learning problems
- data mining
- neural network