Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning.
Sam LobelAkhil BagariaGeorge KonidarisPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- active exploration
- action selection
- function approximation
- learning algorithm
- exploration strategy
- autonomous learning
- reinforcement learning algorithms
- neural network
- real time
- model based reinforcement learning
- exploration exploitation tradeoff
- exploration exploitation
- accurate estimation
- robust estimation
- state space
- mobile devices
- multi agent
- search engine
- data mining