Pinned Loading

1. doom-net-pytorch doom-net-pytorch Public

   Reinforcement learning models in ViZDoom environment

   Python 130 19

2. policy-autoencoder policy-autoencoder Public

   Policy auto-encoder model that learns approximation of state transition and policy functions

   Lua 2

3. geswall geswall Public

   GeSWall, Intrusion Prevention System

   C++ 22 13

4. defence defence Public

   Pascal

5. hard-attention hard-attention Public

   Leaning hard attention model by policy gradient with rewards based on active inference.

   Lua 22 7

6. old_games old_games Public

   Assembly