On the Analysis of Complex Backup Strategies in Monte Carlo Tree Search
By Piyush Khandelwal, Elad Liebman, Scott Niekum, Peter Stone. 2016
22 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Thomas Unterthiner
- Michael Widrich
- José Antonio Arjona-Medina
- J. Urgen Schmidhuber
- Wojciech Samek
- Michael Gillhofer
- Yoshua Bengio
- Sepp Hochreiter
Citations in the corpus
- RUDDER: Return Decomposition for Delayed Rewards (2018, methodology): “obtained by 100 simulated trajectories that start at this node. These simulations use a uniform random policy whose average Return is calculated. The backpropagation step uses the MCTS(1) update rule [66]. The tree policies exploration constant is p 2. Q-learning and MC use a learning rate of 0:3 an”