Optimizing Data Collection in Deep Reinforcement Learning.
James GleesonDaniel SniderYvonne YangMoshe GabelEyal de LaraGennady PekhimenkoPublished in: CoRR (2022)
Keyphrases
- data collection
- reinforcement learning
- function approximation
- sensor networks
- exploration exploitation tradeoff
- collecting data
- state space
- data analysis
- collected data
- learning algorithm
- wireless sensor networks
- multi agent reinforcement learning
- reinforcement learning algorithms
- temporal difference
- website
- model free
- transfer learning
- optimal policy
- machine learning
- optimal control
- data entry
- direct policy search
- databases
- neural network
- action selection
- information retrieval
- partially observable
- deep learning
- learning agents
- dynamic programming
- search engine
- robotic control