upload via upload_folder 2025-07-26T20:09:33.953403+00:00

README.md

@@ -0,0 +1,35 @@
+---
+env_name: Pendulum-v1
+tags:
+- Pendulum-v1
+- sac
+- reinforcement-learning
+- custom-implementation
+- SAC
+- Pendulum
+model-index:
+- name: SAC-PendulumV1
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+    metrics:
+    - type: mean_reward
+      value: -129.63 +/- 63.60
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **Pendulum-v1**
+This is a trained model of a **SAC** agent playing **Pendulum-v1**.
+
+## Usage
+
+model = load_from_hub(repo_id="winkin119/SAC-PendulumV1", filename="sac_pendulum.pth")
+
+
+env = gym.make("Pendulum-v1")
+...

eval_result.json

@@ -0,0 +1,6 @@
+{
+    "mean_reward": -129.63262623823556,
+    "std_reward": 63.59632357260991,
+    "datetime": "2025-07-26T19:43:29.520758+00:00",
+    "train_duration_min": "1.27"
+}

params.json

@@ -0,0 +1,41 @@
+{
+    "env_config": {
+        "env_id": "Pendulum-v1",
+        "env_kwargs": {},
+        "max_steps": null,
+        "use_image": false,
+        "vector_env_num": 6,
+        "use_multi_processing": true,
+        "image_shape": null,
+        "frame_stack": 1,
+        "frame_skip": 1,
+        "training_render_mode": null
+    },
+    "device": "cpu",
+    "learning_rate": 0.0003,
+    "gamma": 0.99,
+    "checkpoint_pathname": "",
+    "max_grad_norm": 0.5,
+    "log_interval": 100,
+    "eval_episodes": 50,
+    "eval_random_seed": 42,
+    "eval_video_num": 10,
+    "total_steps": 120000,
+    "hidden_sizes": [
+        128,
+        128
+    ],
+    "use_layer_norm": true,
+    "critic_lr": 0.0003,
+    "replay_buffer_capacity": 96000,
+    "batch_size": 128,
+    "update_start_step": 10000,
+    "alpha": 0.2,
+    "auto_tune_alpha": true,
+    "alpha_lr": 0.0003,
+    "target_entropy": -1.0,
+    "tau": 0.005,
+    "max_action": 2.0,
+    "log_std_min": -20,
+    "log_std_max": 2
+}

sac_pendulum.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb09c57c3b134e8c76147a7e95f2c44cd60fe0acd0f67ea16c658786a814d744
+size 77597