<--- Back to Details
| First Page | Document Content | |
|---|---|---|
 Date: 2015-12-12 00:05:18Mathematics Mathematical optimization Dynamic programming Mathematical analysis Equations Operations research Systems theory Stochastic control Bellman equation Markov decision process Q-learning Reinforcement learning |
Add to Reading List |
Increasing the Action Gap: New Operators for Reinforcement Learning Marc G. Bellemare and Georg Ostrovski and Arthur Guez Philip S. Thomas∗ and R´emi Munos Google DeepMind {bellemare,ostrovski,aguez,munos}@google.com;
