upload via upload_folder 2025-08-03T12:41:39.016066+00:00

README.md

@@ -5,8 +5,9 @@ tags:
 - sac
 - reinforcement-learning
 - custom-implementation
-- SAC
-- Pendulum
+- policy-gradient
+- pytorch
+- ddpg
 model-index:
 - name: SAC-PendulumV1
   results:
@@ -27,9 +28,21 @@ model-index:
 This is a trained model of a **SAC** agent playing **Pendulum-v1**.
 
 ## Usage
+# create the conda env in https://github.com/GeneHit/drl_practice
+```bash
+conda create -n drl python=3.10
+conda activate drl
+python -m pip install -r requirements.txt
+```
 
-model = load_from_hub(repo_id="winkin119/SAC-PendulumV1", filename="sac_pendulum.pth")
-
+# load the full model
+```python
+model = load_from_hub(repo_id="winkin119/SAC-PendulumV1", filename="full_model.pt")
 
+# Create the environment. 
 env = gym.make("Pendulum-v1")
+state, _ = env.reset()
+action = model.action(state)
 ...
+```
+There is also a state dict version of the model.

full_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34af57bb8c1b527b14dd6139ddc5fa9ff6e4422b8fc835d9ac4d8664e6cf167
+size 77557

state_dict.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091c9500fd325af86f13110fdd0737d16f1beeb330bf227f6ef6bf57e6678124
+size 75445