Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								2fdde6eb6b
							
							Removed pytorch_rl dependency on OpenAI baselines to make install easier
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								ca85d1086d
							
							Added recurrent MLP policy
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								c4257fd34c
							
							Minor change
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								780c75e2cd
							
							RL code updates from upstream repos, removed Atari dependencies
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								21c0eaa8c7
							
							Renamed pytorch-rl to pytorch_rl for Python importability
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								723359da33
							
							Removed waitEnds flag
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								4267b1d39e
							
							Completed PutNear environment
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								87a0befdbf
							
							Added ability to drop/put down objects. Started work on PutNear env.
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								5fd284ff88
							
							Minor refactoring for environment creation process
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								0ecec6bce9
							
							Minor bugfix on FlatObsWrapper
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								73e6d3d2f1
							
							Made adjustments to GoToObject based on GoToDoor env
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								3d0c94f876
							
							Removed "advice" from observations. Randomized GoToDoor room size.
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								a99538576b
							
							Update README.md
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								c8b35cb515
							
							Updated README
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								ad4358543a
							
							Added go to door environment to README
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								f2dd5adfc3
							
							Added color names list to minigrid.py
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								1a80488ad0
							
							Fixed bug, improved reward function in GoToDoor env
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								c75d108362
							
							Added more configs for GoToDoor environment
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								c4f68f309b
							
							Implemented GoToDoor environment
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								28df92e70d
							
							Fixed issues with run_tests.py, grid encode/decode
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								e7e870ce2d
							
							Fixed issues with wrappers
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								360927639b
							
							Added wrapper for one-hot string encoding. Fixed bugs in goto env.
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								116bfb2d4b
							
							Completed implementation of goto env
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								67acc5ff18
							
							Started work on goto env
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								a05dd9456f
							
							Split out simple_envs.py
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								d4d83a9bf6
							
							Added warning if cuda is disabled, to avoid silent failure
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								32535cc145
							
							Changed reward range for fetch environment
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								e02777d81b
							
							Added function to encode observations to FetchEnv
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								16698be044
							
							Added 5x5 config for the fetch environment
						 | 
						%!s(int64=7) %!d(string=hai) anos | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								80b3178610
							
							Moved rl code to pytorch-rl. Fixed warnings. Fixed issue w/ flat obs.
						 | 
						%!s(int64=7) %!d(string=hai) anos |