diff --git a/README.md b/README.md
index 65edde2..ada423a 100644
--- a/README.md
+++ b/README.md
@@ -363,7 +363,7 @@ The recommended end-to-end workflow for training an RL operator is an iterative
 ```
 ┌─────────────────────────────────────────────────────────────┐
 │  1. Human dataset collection                                │
-│     Play the game: start up the reactor, operate it across │
+│     Play the game: start up the reactor, operate it across  │
 │     a range of states. NuCon records state transitions.     │
 └───────────────────────┬─────────────────────────────────────┘
                         │
@@ -376,7 +376,7 @@ The recommended end-to-end workflow for training an RL operator is an iterative
 └───────────────────────┬─────────────────────────────────────┘
                         │
               ┌─────────▼──────────┐
-              │   3. Train RL      │◄──────────────────────┐
+              │   3. Train RL      │◄───────────────────────┐
               │   in simulator     │                        │
               │   (fast, many      │                        │
               │   trajectories)    │                        │