The QLBS Q-Learner Goes NuQLear: Fitted Q Iteration, Inverse RL, and Option Portfolios.
Igor HalperinPublished in: CoRR (2018)
Keyphrases
- complex domains
- fitted q iteration
- reinforcement learning
- learning process
- learning environment
- function approximation
- adaptive learning
- model free
- state space
- e learning
- markov decision processes
- portfolio selection
- transfer learning
- learning algorithm
- language learning
- rl algorithms
- temporal difference
- learning problems
- portfolio optimization
- portfolio assessment
- dynamic programming
- reinforcement learning algorithms
- multi agent
- social learning
- option pricing
- learning materials