Composable Modular Reinforcement Learning.
Christopher L. SimpkinsCharles L. Isbell Jr.Published in: AAAI (2019)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- reinforcement learning algorithms
- markov decision processes
- machine learning
- control problems
- information retrieval
- learning algorithm
- dynamic programming
- temporal difference learning
- optimal policy
- multi agent
- learning problems
- temporal difference
- decision making
- search engine
- action selection
- partially observable
- neural network
- action space
- function approximators
- learning process
- continuous state
- multi agent reinforcement learning
- modular structure
- perceptual aliasing