ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning and Snapshot Ensembling.
Christopher SchulzeMarcus SchulzePublished in: IntelliSys (1) (2018)
Keyphrases
- reinforcement learning
- cooperative
- multi agent
- learning algorithm
- state space
- learning curve
- stochastic approximation
- possibilistic logic
- function approximation
- predictive accuracy
- user experience
- neural network
- optimal policy
- action selection
- classifier ensemble
- sufficient conditions
- multi class
- control system
- potential field
- bucket brigade