A sandbox repo to experiment with Reinforcement Learning
(actual DQN paper)
https://www.nature.com/nature/journal/v518/n7540/pdf/nature14236.pdf
-multiagent stuff:
https://arxiv.org/abs/1511.06581
https://arxiv.org/pdf/1511.08779.pdf
https://arxiv.org/pdf/1509.02971.pdf ** continuous action spaces
https://arxiv.org/abs/1511.05952 ** prioritized experience replay
http://proceedings.mlr.press/v48/mniha16.pdf ** way faster (paralell) way of doing this
https://arxiv.org/pdf/1509.06461.pdf (double dqn paper)
https://arxiv.org/pdf/1707.06203.pdf (deepmind imagination augmentation 2017)
http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14456/14385 (CMU doom paper)