Variance Penalized On-Policy and Off-Policy Actor-Critic.
Arushi JainGandharv PatilAyush JainKhimya KhetarpalDoina PrecupPublished in: CoRR (2021)
Keyphrases
- actor critic
- policy gradient
- reinforcement learning
- variance reduction
- approximate dynamic programming
- optimal control
- temporal difference
- gradient method
- policy iteration
- neuro fuzzy
- policy gradient methods
- reinforcement learning algorithms
- least squares
- function approximation
- average reward
- monte carlo
- state space
- linear program
- model free
- fuzzy logic
- sample size
- markov decision process
- partially observable markov decision processes
- decision making
- optimal policy
- dynamic programming
- reinforcement learning problems
- natural actor critic