Neuro-symbolic Meta Reinforcement Learning for Trading.
S. I HariniGautam ShroffAshwin SrinivasanPrayushi FalduLovekesh VigPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- electronic commerce
- model free
- markov decision processes
- neural network
- artificial neural networks
- reinforcement learning algorithms
- neuro fuzzy
- temporal difference
- learning process
- state space
- learning algorithm
- optimal policy
- robotic control
- meta reasoning
- action selection
- machine learning
- meta level
- multi agent reinforcement learning
- neural learning
- stock data
- multi agent
- high level
- state transition
- transfer learning
- markov decision process
- trading systems
- function approximators
- temporal difference learning
- stochastic approximation
- connectionist models
- transition model