Combining Q-Learning and Search with Amortized Value Estimates.
Jessica B. HamrickVictor BapstAlvaro Sanchez-GonzalezTobias PfaffTheophane WeberLars BuesingPeter W. BattagliaPublished in: CoRR (2019)
Keyphrases
- search algorithm
- search space
- reinforcement learning
- cooperative
- search tools
- solution space
- multi agent
- search strategies
- genetic algorithm
- stochastic approximation
- search efficiency
- learning rate
- search strategy
- neural network
- information seeking
- information retrieval systems
- computational complexity
- action selection
- learning algorithm