Source code of DQN 3.0, a Lua-based deep reinforcement learning architecture for reproducing the experiments described in our Nature paper 'Human-level control through deep reinforcement learning'.
25 Feb 2015
Unsupervised learning & generative models
George Papamakarios, Eric Nalisnick, et al. arXiv 2019
We present a new method for training reinforcement learning agents from human feedback in the presence of unknown unsafe...
13 Dec 2019