Push Reinforce agent to the Hub

README.md

@@ -5,7 +5,7 @@ tags:
 - deep-reinforcement-learning
 - reinforcement-learning
 - custom-implementation
-- deep-rl-class
+- deep-rl-course
 model-index:
 - name: PPO
   results:
@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -217.44 +/- 126.66
+      value: -192.49 +/- 124.42
       name: mean_reward
       verified: false
 ---
@@ -55,8 +55,9 @@ model-index:
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'repo_id': 'jmurphy97/LunarLander-v2'
+'push_to_hf': True
 'batch_size': 512
-'minibatch_size': 128}
+'minibatch_size': 128
+'repo_id': 'jmurphy97/LunarLander-v2'}
   ```
   

logs/events.out.tfevents.1681556515.2373e9397595.4006.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fddee3aea9d97401f4ff4e2b3b4c905fe80b5548a9503f8e76c90ffb4aef9b91
+size 744

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -217.43773267589532, "std_reward": 126.65769659188194, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-15T10:59:08.918246"}
+{"env_id": "LunarLander-v2", "mean_reward": -192.48962821381954, "std_reward": 124.41960222935549, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-15T11:02:00.167683"}