brozek/GymInteract
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Commit graph

  • 547620e949
         Create LICENSE master Brandon Rozek 2020-03-29 14:48:18 -0400
  • 66496fe0d8 Changes from honors thesis Brandon Rozek 2020-03-23 20:02:06 -0400
  • a44b981e55 Small import error fix Brandon Rozek 2019-11-17 18:39:28 -0500
  • 8dd9ca617e Incorporated concepts from the paper "Deep Q-Learning From Demonstrations" Brandon Rozek 2019-11-17 18:36:35 -0500
  • 744656aaa9 Updated configs and fixed threading issues Brandon Rozek 2019-11-05 07:09:49 -0500
  • 32862e4d79 Began separating config & networks, F1 for pausing, text functions, and more sneaky agent stuff Brandon Rozek 2019-10-27 20:42:37 -0400
  • d78892e62c SneakyTrain uses separate replay buffer Scripts were cleaned up considerably and comments were added Brandon Rozek 2019-10-23 21:53:20 -0400
  • b7aa4a4ec6 Updated GymInteract to introduce a form of hidden training between showing the human play the game and the computer Brandon Rozek 2019-10-20 09:06:42 -0400
  • 1bf2c15542 Back and forth between computer play and human play while training an agent Brandon Rozek 2019-09-21 19:03:00 -0400