Discount Factor as a Regularizer in Reinforcement Learning.
Ron AmitRon MeirKamil CiosekPublished in: CoRR (2020)
Keyphrases
- discount factor
- reinforcement learning
- optimal policy
- markov decision processes
- markov decision problems
- partially observable
- average reward
- state space
- reinforcement learning algorithms
- infinite horizon
- policy iteration
- function approximation
- finite state
- long run
- markov decision process
- dynamic programming
- decision problems
- learning algorithm
- model free
- supervised learning
- semi supervised
- multi agent
- action space
- neural network
- partially observable markov decision processes
- decision processes
- lost sales