Commit History

Autor SHA1 Mensaxe Data
  Maxime Chevalier-Boisvert c53358bf8f Fixed bug in environment string representation %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert b6ffc9ba38 Added colored floor tile the agent can walk over %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert e270e76ee5 Added object position tracking %!s(int64=7) %!d(string=hai) anos
  Lucas Willems ea6416989f Add `_rand_float` method (#10) %!s(int64=7) %!d(string=hai) anos
  Lucas Willems c125ca7998 Minimum reward when success is now 0.1 (#9) %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 290ab259e4 Modified RedBlueDoor env to enforce door opening sequence %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert c99822121e Added reward penalty based on number of time steps taken %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 636226f90e Renamed wait action to done %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 0ad70c61dd Added _rand_subset method to MiniGridEnv %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 40f29632c2 Added ability to render observations at any resolution %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 041225e96b Added position randomization to RedBlueDoors env. Updated README. %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 216fe87800 Merge pull request #8 from lcswillems/master %!s(int64=7) %!d(string=hai) anos
  Lucas Willems 82d080fa8b Merge remote-tracking branch 'upstream/master' %!s(int64=7) %!d(string=hai) anos
  Lucas Willems ec123f87cf Add a RedBlueDoors environment %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 2b243b906f Update README.md %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 342b3c96f1 Fixed bug in place_agent %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 5d88cb4376 Doors can now be closed back after they are opened %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 4f4992265b Fixed issue wrt agent view size pointed out by Anirudh %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 2190ce0b59 Full map correctly highlights cells visible to the agent %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 076e074b0a Changed timestep limits based on feedback from Rosemary Ke %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 6b513362e6 Added gen_obs_grid method which outputs visibility mask %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert a6ece826ce Removed old visibility code %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 76b43b7534 Added DIR_TO_VEC array. Agent position is now a numpy array. %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert d5d117bb78 Added goal_pos variable to MultiRoomEnv %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 146fd10741 Made reward_range the same for all environments, rewards are in [0, 1] %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert fe469bb1cc Added MiniGrid._rand_color method %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 30c97ffc57 Added _rand_bool() method to MiniGrid %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert d562fb8f82 Fixup. Default random seed should be fixed, deterministic. %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert 9b585b9b51 Added seed argument to MiniGrid constructor, removed RoomGrid %!s(int64=7) %!d(string=hai) anos
  Maxime Chevalier-Boisvert da1e2c5c5e Increased max_steps on Empty & DoorKey envs %!s(int64=7) %!d(string=hai) anos