AgentNet
AgentNet copied to clipboard
yandexdataschool
Deep Reinforcement Learning library for humans
It would be really nice if we could have an example that re-implements the original [DQN ](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf) paper exactly. The Ms. PacMan one is pretty close but AFAIK it has...
The idea comes from lasagne: https://github.com/Lasagne/Lasagne/issues/611 Some functions have the same functional, but 2 backends can return different format of results. However, it is not a big issue if we...
Universe supports vectorized environments. Would be great to support them in Gym pool
Right now recurrent memory cells have clumsy weight management. - manual weight initialization during layer creation https://github.com/yandexdataschool/AgentNet/blob/master/agentnet/memory/rnn.py#L260-L266 - inside there's more than one layer so one can't simply get lstm.W_this_to_that...
Metadata
Owner
Metadata
Deep Reinforcement Learning library for humans