Upload PPO agent

README.md

@@ -0,0 +1,59 @@
+---
+tags:
+- LunarLander-v3
+- ppo
+- reinforcement-learning
+- cleanrl
+- colab
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v3
+      type: LunarLander-v3
+    metrics:
+    - type: mean_reward
+      value: -200.82 +/- 95.02
+      name: mean_reward
+      verified: false
+---
+# PPO Agent for LunarLander-v3
+
+Mean reward: -200.82 ± 95.02
+
+```python
+{
+  "exp_name": "ppo_colab",
+  "seed": 1,
+  "torch_deterministic": true,
+  "cuda": true,
+  "track": false,
+  "wandb_project_name": "cleanRL",
+  "wandb_entity": null,
+  "capture_video": true,
+  "env_id": "LunarLander-v3",
+  "total_timesteps": 10,
+  "learning_rate": 0.00025,
+  "num_envs": 1,
+  "num_steps": 128,
+  "anneal_lr": true,
+  "gae": true,
+  "gamma": 0.99,
+  "gae_lambda": 0.95,
+  "num_minibatches": 1,
+  "update_epochs": 4,
+  "norm_adv": true,
+  "clip_coef": 0.2,
+  "clip_vloss": true,
+  "ent_coef": 0.01,
+  "vf_coef": 0.5,
+  "max_grad_norm": 0.5,
+  "target_kl": null,
+  "repo_id": "Akchunks/LunarLander-v2",
+  "batch_size": 128,
+  "minibatch_size": 128
+}
+```

logs/events.out.tfevents.1748689997.13543feeb83d.188.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac50032600feacaf912cefbbe03936d25ed8cec930556df5116de92f680399a
+size 88

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701d954461323cfbc3d99b1b5933e746fe6c44ac2196732d35fbc3e401205b23
+size 42898

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v3", "mean_reward": -200.8202600548159, "std_reward": 95.0173797879124, "n_eval_episodes": 10, "eval_datetime": "2025-05-31T11:15:14.484207"}