Add Unit 1 evaluation results

README.md

@@ -0,0 +1,38 @@
+---
+tags:
+- reinforcement-learning
+- stable-baselines3
+- LunarLander-v2
+- deep-rl-course
+model-index:
+- name: ppo-LunarLander-v2
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: "269.79 +/- 20.99"
+      name: mean_reward
+---
+
+# PPO LunarLander-v2
+
+Deep Reinforcement Learning Course — Unit 1.
+
+## Evaluation
+
+Environment: `LunarLander-v2`
+
+Mean reward: `269.79`
+
+Standard deviation: `20.99`
+
+Course score: `248.80`
+
+Evaluation episodes: `20`
+
+Training timesteps: `1,000,000`