Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								0a9d6d8631
							
							Enabling Travis automated tests
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								977b25acfc
							
							Merge pull request #4 from lcswillems/master
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Lucas Willems
							
						 | 
						
							
							
								d210a56edd
							
							Merged `prettyencode`, `prettystring` and `__str__` Grid methods into one `__str__` MiniGridEnv method.
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Lucas Willems
							
						 | 
						
							
							
								063b2dda6c
							
							`prettyencode`, `prettystring` and `__str__` added to Grid.
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								44dedaeb16
							
							Added max_steps parameter to RoomGrid environment
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								e84bba090e
							
							Added operator == definition for grids
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								fe1dfc2231
							
							Added direction/compass to observation
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								63289b521c
							
							Split toggle into pickup/drop/toggle actions
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								2abfef3b02
							
							Removed FourRooomQA environment
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								2f34df4e42
							
							Randomized door positions in RoomGrid
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								2b9f8f57fd
							
							Merge pull request #3 from lcswillems/master
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Lucas Willems
							
						 | 
						
							
							
								92922b13f7
							
							Fixed bugs with `Goal` `overlap` method.
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Lucas Willems
							
						 | 
						
							
							
								f09b7944dd
							
							`goal` can now overlap.
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								54012927de
							
							Added support for locked doors in RoomGrid
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								257b4d4078
							
							Modifications to RoomGrid for level generation in Baby AI
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								3c52268b00
							
							Progress on RoomGrid-v0 env
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								99931d11d0
							
							Renamed Playground-v1 to RoomGrid-v0
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								cdb80a5d30
							
							Started work on Playground-v1 environment for curriculum learning
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								e00764ebf8
							
							Lazily importing visdom
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								340c03a446
							
							Cleaned up and simplified _genGrid functions
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								3096a3b7f4
							
							Updated README
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								0e496fe636
							
							Fixed visdom visualization code
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								e5f35ea056
							
							Randomized agent position in playground environment
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								1e5d26e4c0
							
							Fixed issue with environment seeding
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								c4049b13ed
							
							Added Playground-v0 environment for experiments
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								5a6461ff2e
							
							Added GRU to policy, made model larger.
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								17eba78e33
							
							Fixed pyqt5 package version
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								2cdc42ac43
							
							Modified reward range for fetch environment
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								2b1d180dda
							
							Corrected reward ranges for environments
						 | 
						7 rokov pred | 
					
				
					
						
							
								   Maxime Chevalier-Boisvert
							
						 | 
						
							
							
								24f7678f57
							
							Update README.md
						 | 
						7 rokov pred |