Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,11 +13,11 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 73.40 +/- 59.80
+      value: -28.41 +/- 32.45
       name: mean_reward
       verified: false
 ---

logs/events.out.tfevents.1712109659.autoreg-5919151.dyn.wpi.edu.60849.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4166cda8c673185df0cde6a0c179f67e50440aa2fc90c432eb8fbd3e2658e9fd
+size 25146

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd2f5cd9a92d295cbb24a54da2198bccfddb449e28e8234e44747a4dc520527
-size 40338
+oid sha256:22621ce00620569bd7e38bc408ffb1e67be0e386ba3bb0d362d3dda052f145c2
+size 42898

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 73.40071237756011, "std_reward": 59.80214989590959, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-02T21:33:36.479210"}
+{"env_id": "LunarLander-v2", "mean_reward": -28.405987582014955, "std_reward": 32.447953043687065, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-02T22:01:04.825114"}