Browse Source

Update README.md

Maxime Chevalier-Boisvert 7 years ago
parent
commit
a99538576b
1 changed files with 4 additions and 4 deletions
  1. 4 4
      README.md

+ 4 - 4
README.md

@@ -112,7 +112,7 @@ Registered configurations:
 - `MiniGrid-Empty-16x16-v0`
 - `MiniGrid-Empty-16x16-v0`
 
 
 <p align="center">
 <p align="center">
-<img src="/figures/empty-env.png">
+<img src="/figures/empty-env.png" width=250>
 </p>
 </p>
 
 
 This environment is an empty room, and the goal of the agent is to reach the
 This environment is an empty room, and the goal of the agent is to reach the
@@ -153,7 +153,7 @@ square the agent must get to. This environment is extremely difficult to
 solve using classical RL. However, by gradually increasing the number of
 solve using classical RL. However, by gradually increasing the number of
 rooms and building a curriculum, the environment can be solved.
 rooms and building a curriculum, the environment can be solved.
 
 
-### Go to door environment
+### Go-to-door environment
 
 
 Registered configurations:
 Registered configurations:
 - `MiniGrid-GoToDoor-5x5-v0`
 - `MiniGrid-GoToDoor-5x5-v0`
@@ -161,7 +161,7 @@ Registered configurations:
 - `MiniGrid-GoToDoor-8x8-v0`
 - `MiniGrid-GoToDoor-8x8-v0`
 
 
 <p align="center">
 <p align="center">
-<img src="/figures/gotodoor-6x6.png">
+<img src="/figures/gotodoor-6x6.png" width=400>
 </p>
 </p>
 
 
 This environment is a room with four doors, one on each wall. The agent
 This environment is a room with four doors, one on each wall. The agent
@@ -176,7 +176,7 @@ Registered configurations:
 - `MiniGrid-Fetch-8x8-N3-v0`
 - `MiniGrid-Fetch-8x8-N3-v0`
 
 
 <p align="center">
 <p align="center">
-<img src="/figures/fetch-env.png" width=392 height=269>
+<img src="/figures/fetch-env.png" width=450>
 </p>
 </p>
 
 
 This environment has multiple objects of assorted types and colors. The
 This environment has multiple objects of assorted types and colors. The