Update checkpoint (iter 8900)

README.md

@@ -0,0 +1,33 @@
+---
+license: mit
+library_name: pytorch
+tags:
+  - reinforcement-learning
+  - locomotion
+  - robotics
+  - g1
+---
+
+# g1-fight
+
+PyTorch checkpoint for a G1 humanoid locomotion policy trained with
+ADD (Adversarial Differential of Discriminators).
+
+## Checkpoint info
+
+| Key | Value |
+|-----|-------|
+| Training iterations | `8,900` |
+| Total environment samples | `4,666,687,488` |
+| Number of parameters | `1,983,104` |
+
+## Usage
+
+```python
+import torch
+
+checkpoint = torch.load("model.pt", map_location="cpu")
+state_dict = checkpoint["model"]
+# Load into your agent:
+# agent.load_state_dict(state_dict)
+```

metadata.json

@@ -0,0 +1,5 @@
+{
+  "training_iterations": 8900,
+  "total_samples": 4666687488,
+  "num_parameters": 1983104
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6f5a4545a1da9db128534c5310b31a18cbb01edfffe24a4a49a97f28a0156a
+size 7943646