upload via upload_folder 2025-07-29T12:35:20.331691+00:00

README.md

@@ -2,11 +2,13 @@
 env_name: CartPole-v1
 tags:
 - CartPole-v1
-- reinforce
+- vanilla-reinforce
 - reinforcement-learning
 - custom-implementation
 - policy-gradient
 - pytorch
+- vanilla
+- monte-carlo
 model-index:
 - name: Reinforce-CartPole
   results:
@@ -18,7 +20,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 439.30 +/- 74.67
+      value: 500.00 +/- 0.00
       name: mean_reward
       verified: false
 ---

eval_result.json

@@ -1 +1,6 @@
-{"mean_reward": 439.3, "std_reward": 74.66933774984214, "date": "2025-07-11 21:09:00"}
+{
+    "mean_reward": 500.0,
+    "std_reward": 0.0,
+    "datetime": "2025-07-29T12:27:37.503071+00:00",
+    "train_duration_min": "1.06"
+}

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e077ce25f157f2b41dfa7b3f683aec0c1109c905d0ebf9ceef11d3df2b36fe
+size 74365

params.json

@@ -1 +1,37 @@
-{"hyper_params": {"global_episode": 1000, "lr": 0.0001, "gamma": 0.99, "grad_acc": 1, "num_envs": 2, "use_multi_processing": true}, "env_params": {"env_id": "CartPole-v1", "max_steps": 1000, "observation_space.shape": [4], "action_space": 2}, "eval_params": {"eval_episodes": 20, "eval_seed": [1, 55, 44, 23, 12, 34, 86, 78, 90, 100, 166, 127, 134, 145, 151, 115, 178, 189, 190, 200]}, "output_params": {"output_dir": "results/exercise3_reinforce/cartpole/", "save_result": true, "model_filename": "reinforce.pth", "params_filename": "params.json", "train_result_filename": "train_result.json", "eval_result_filename": "eval_result.json"}, "hub_params": {"repo_id": "Reinforce-CartPole"}, "_notes": ["checkpoint_pathname: results/exercise3_reinforce/cartpole/reinforce.pth"]}
+{
+    "env_config": {
+        "env_id": "CartPole-v1",
+        "env_kwargs": {},
+        "max_steps": null,
+        "normalize_obs": false,
+        "use_image": false,
+        "vector_env_num": null,
+        "use_multi_processing": false,
+        "image_shape": null,
+        "frame_stack": 1,
+        "frame_skip": 1,
+        "training_render_mode": null
+    },
+    "device": "cpu",
+    "learning_rate": 0.0001,
+    "gamma": 0.99,
+    "checkpoint_pathname": "",
+    "max_grad_norm": null,
+    "log_interval": 100,
+    "eval_episodes": 20,
+    "eval_random_seed": 42,
+    "eval_video_num": 10,
+    "episode": 2000,
+    "entropy_coef": {
+        "_type": "LinearSchedule",
+        "_module": "practice.utils_for_coding.scheduler_utils",
+        "_start_e": 0.1,
+        "_end_e": 0.01,
+        "_duration": 2000,
+        "_start_t": 0
+    },
+    "hidden_sizes": [
+        128,
+        128
+    ]
+}

tensorboard/events.out.tfevents.1753791985.winkindeMacBook-Air.local.57654.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141f4b06a8edd5ac46572ca3ad8943f3114d52c57e97da7ffeaf5d93755b63a1
+size 717178