upload via upload_folder 2025-07-27T10:15:35.880859+00:00

.gitattributes

@@ -33,3 +33,4 @@ 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
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+env_name: Walker2d-v5
+tags:
+- Walker2d-v5
+- sac
+- reinforcement-learning
+- custom-implementation
+- Walker2d
+model-index:
+- name: SAC-Walker2dV5
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Walker2d-v5
+      type: Walker2d-v5
+    metrics:
+    - type: mean_reward
+      value: 4150.91 +/- 823.47
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **Walker2d-v5**
+This is a trained model of a **SAC** agent playing **Walker2d-v5**.
+
+## Usage
+
+model = load_from_hub(repo_id="winkin119/SAC-Walker2dV5", filename="sac_walker.pth")
+
+
+env = gym.make("Walker2d-v5")
+...

eval_result.json

@@ -0,0 +1,6 @@
+{
+    "mean_reward": 4150.910494947614,
+    "std_reward": 823.4738749463849,
+    "datetime": "2025-07-26T21:01:59.365966+00:00",
+    "train_duration_min": "54.76"
+}

params.json

@@ -0,0 +1,42 @@
+{
+    "env_config": {
+        "env_id": "Walker2d-v5",
+        "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": 0.995,
+    "checkpoint_pathname": "",
+    "max_grad_norm": 0.5,
+    "log_interval": 100,
+    "eval_episodes": 50,
+    "eval_random_seed": 42,
+    "eval_video_num": 10,
+    "total_steps": 1200000,
+    "hidden_sizes": [
+        256,
+        256,
+        256
+    ],
+    "use_layer_norm": true,
+    "critic_lr": 0.0003,
+    "replay_buffer_capacity": 960000,
+    "batch_size": 256,
+    "update_start_step": 10000,
+    "alpha": 0.2,
+    "auto_tune_alpha": true,
+    "alpha_lr": 0.0003,
+    "target_entropy": -6.0,
+    "tau": 0.005,
+    "max_action": 1.0,
+    "log_std_min": -20,
+    "log_std_max": 2
+}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7626e2ced6ddc0bb19c00948ac2594a044556cc3168b3f22aceb53bf190fc653
+size 1238845

sac_walker.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b4ec498e9814cf6a03cbf35b91030e1c2dc6c11a0e2399f050d7fe5b4a46d4
+size 570421

tensorboard/events.out.tfevents.1753560365.winkindeMacBook-Air.local.4586.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84204083aaf1dba6bcd4250304ba735ecdf32edd209bbd220b41b66bc6fc051c
+size 1622991