Reinforcement Learning in POMDPs With Memoryless Options and Option-Observation Initiation Sets.
Denis SteckelmacherDiederik M. RoijersAnna HarutyunyanPeter VrancxHélène PlisnierAnn NowéPublished in: AAAI (2018)
Keyphrases
- reinforcement learning
- option pricing
- markov decision processes
- policy search
- partially observable markov decision processes
- continuous state
- function approximation
- learning algorithm
- payoff functions
- partially observable
- reinforcement learning algorithms
- black scholes model
- model free
- transfer learning
- policy gradient
- state space
- optimal policy
- learning process
- multi agent
- temporal difference
- optimal control
- finite state
- stock price
- reinforcement learning methods
- markov decision problems
- supervised learning
- dynamic programming
- policy iteration algorithm