HumanCompatibleAI
/

ppo-seals-HalfCheetah-v0

Reinforcement Learning

stable-baselines3

seals/HalfCheetah-v0

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

ppo-seals-HalfCheetah-v0

25.1 MB

Ctrl+K

Ctrl+K

2 contributors

History: 6 commits

ernestum's picture

Initial commit

d432e2b almost 4 years ago

ppo-seals-HalfCheetah-v0
Initial commit almost 4 years ago
.gitattributes

1.44 kB
Add model trained with imitation along with rollouts almost 4 years ago
README.md

2.94 kB
Initial commit almost 4 years ago
args.yml

1.28 kB
Initial commit almost 4 years ago
config.yml

805 Bytes
Initial commit almost 4 years ago
env_kwargs.yml

3 Bytes
Initial commit about 4 years ago
ppo-seals-HalfCheetah-v0.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
172 kB
xet

Initial commit almost 4 years ago
replay.mp4

1.97 MB
xet

Initial commit almost 4 years ago
results.json

159 Bytes
Initial commit almost 4 years ago
rollouts.npz
Pickle imports
- No problematic imports detected
What is a pickle import?
22.8 MB
xet

Update rollouts extension almost 4 years ago
train_eval_metrics.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
33.7 kB
xet

Initial commit almost 4 years ago
vec_normalize.pkl
Detected Pickle imports (8)
- "numpy.core.multiarray._reconstruct",
- "numpy.dtype",
- "gym.spaces.box.Box",
- "stable_baselines3.common.running_mean_std.RunningMeanStd",
- "numpy.random._pickle.__randomstate_ctor",
- "stable_baselines3.common.vec_env.vec_normalize.VecNormalize",
- "numpy.core.multiarray.scalar",
- "numpy.ndarray"
How to fix it?
4.37 kB
xet

Initial commit almost 4 years ago