igorcheb
/

REINFORCE-LunarLanderContinuous-v2

Reinforcement Learning

LunarLanderContinuous-v2

custom-implementation

Eval Results (legacy)

Model card Files Files and versions

REINFORCE-LunarLanderContinuous-v2

43.8 MB

Ctrl+K

Ctrl+K

1 contributor

History: 28 commits

This model has 1 file scanned as unsafe.

igorcheb's picture

Update README.md

00424e6 over 3 years ago

.gitattributes

1.57 kB
Upload replay.gif over 3 years ago
README.md

1.61 kB
Update README.md over 3 years ago
agent_class.py

1.45 kB
Update agent_class.py over 3 years ago
best_reinforce_lunar_lander_cont_model_269.402.pt
Detected Pickle imports (9)
- "torch._utils._rebuild_tensor_v2",
- "__main__.ParameterisedPolicy",
- "torch.nn.modules.activation.ELU",
- "torch.nn.modules.linear.Linear",
- "torch.FloatStorage",
- "torch.nn.modules.activation.ReLU",
- "torch._utils._rebuild_parameter",
- "__builtin__.set",
- "collections.OrderedDict"
How to fix it?
148 kB
xet

Upload . with huggingface_hub over 3 years ago
hyperparameters.json

139 Bytes
Upload . with huggingface_hub over 3 years ago
replay.gif

42.7 MB
xet

Upload replay.gif over 3 years ago
replay.mp4

834 kB
xet

Upload . with huggingface_hub over 3 years ago
training.py

3.77 kB
Create training.py over 3 years ago
training_graph.jpg

129 kB
Upload training_graph.jpg over 3 years ago