Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach.
Silviu PitisPublished in: CoRR (2019)
Keyphrases
- discount factor
- reinforcement learning
- markov decision processes
- optimal policy
- markov decision problems
- partially observable
- average reward
- state space
- reinforcement learning algorithms
- policy iteration
- decision problems
- function approximation
- model free
- finite state
- infinite horizon
- multi agent
- long run
- learning algorithm
- transfer learning
- function approximators
- optimal control
- temporal difference
- reward function
- dynamical systems
- average cost
- sufficient conditions
- linear programming
- supervised learning
- machine learning