Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Weidong-Huang
/
SafeDreamer
like
1
Reinforcement Learning
safe reinforcement learning
world model
safety control
model-based reinforcement learning
arxiv:
2307.07176
arxiv:
1910.09700
License:
apache-2.0
Model card
Files
Files and versions
Community
b17fcfe
SafeDreamer
/
unsafe_dreamerv3
2 contributors
History:
2 commits
Weidong-Huang
dreamerv3 carbutton ckpt
b17fcfe
verified
10 months ago
20240327-000000_dreamerv3_safetygym_SafetyCartButton1-v0_0.jsonl
pickle
Detected Pickle imports (6)
"optax._src.wrappers.ApplyIfFiniteState"
,
"optax._src.transform.ScaleByAdamState"
,
"optax._src.base.EmptyState"
,
"numpy.ndarray"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
How to fix it?
340 MB
LFS
dreamerv3 carbutton ckpt
10 months ago
20240327-000000_dreamerv3_safetygym_SafetyCartButton2-v0_0.jsonl
pickle
Detected Pickle imports (6)
"optax._src.wrappers.ApplyIfFiniteState"
,
"optax._src.transform.ScaleByAdamState"
,
"optax._src.base.EmptyState"
,
"numpy.ndarray"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
How to fix it?
340 MB
LFS
dreamerv3 carbutton ckpt
10 months ago
README.md
Safe
11 Bytes
feat:unsafe_dreamerv3
10 months ago