Transition Based Discount Factor for Model Free Algorithms in Reinforcement Learning.
Abhinav SharmaRuchir GuptaK. LakshmananAtul GuptaPublished in: Symmetry (2021)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- policy iteration
- function approximation
- rl algorithms
- temporal difference
- policy evaluation
- markov decision processes
- average reward
- optimal policy
- learning problems
- least squares
- computational complexity
- data mining
- neural network
- state space
- reinforcement learning methods
- machine learning