Honey. I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL.
Siddharth MysoreBassel El MabsoutRenato MancusoKate SaenkoPublished in: CoG (2021)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- approximate dynamic programming
- temporal difference
- optimal control
- neuro fuzzy
- reinforcement learning algorithms
- gradient method
- function approximation
- policy iteration
- state space
- rl algorithms
- markov decision processes
- model free
- step size
- average reward
- dynamic programming
- neural network
- control problems
- evaluation function
- long run
- control strategy
- monte carlo
- optimal policy
- active learning
- multi agent
- decision making