run trail

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- CartPole-v1
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: tao-ppo-CartPole-v1
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 254.10 +/- 29.91
+      name: mean_reward
+      verified: false
+---
+
+    # Agent playing **CartPole-v1**
+    

hyperparameters.json

@@ -0,0 +1 @@
+{"training": false, "model_name": "PPO", "track": false, "wandb_project_name": "tao", "wandb_entity": null, "env_id": "CartPole-v1", "capture_video": false, "total_timesteps": 500000, "learning_rate": 0.00025, "num_envs": 4, "num_steps": 128, "anneal_lr": true, "gamma": 0.99, "gae_lambda": 0.95, "num_minibatches": 4, "update_epochs": 4, "norm_adv": true, "clip_range": 0.2, "entropy_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "target_kl": null, "seed": 1, "run_name": "CartPole-v1__PPO__1__500000", "device": "cpu", "torch_deterministic": true, "batch_size": 512, "minibatch_size": 128}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfff2411866bdf14cd72f3fc93c85c3769ff70a7735f8d2ad2daa2749bfecf10
+size 39909

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767b346e9a995d9d733706e2256b54d12686cf3dddd2c35c960b123adf080e58
+size 57900

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 254.10000610351562, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-27T17:51:03.873785"}