linker81
/

q-learning-FrozenLake-v1-4x4-no-slippery

Reinforcement Learning FrozenLake-v1-4x4-no_slippery q-learning custom-implementation Eval Results

Model card Files Files and versions Community

q-learning-FrozenLake-v1-4x4-no-slippery

1 contributor

History: 3 commits

This model has one file that has been marked as unsafe.

View unsafe files

q-learning.pkl

linker81's picture

Upload q-learning trained agent for FrozenLake-v1-4x4-no-slippery

1439bf1 8 months ago

.gitattributes

1.27 kB Upload q-learning trained agent for FrozenLake-v1-4x4-no-slippery 8 months ago
README.md

991 Bytes Upload q-learning trained agent for FrozenLake-v1-4x4-no-slippery 8 months ago
q-learning.pkl
Detected Pickle imports (3)
- "unknown.dtype",
- "numpy.core.multiarray._reconstruct",
- "numpy.ndarray"
How to fix it?
933 Bytes
LFS
Upload q-learning trained agent for FrozenLake-v1-4x4-no-slippery 8 months ago
replay.mp4

28.7 kB
LFS
Upload q-learning trained agent for FrozenLake-v1-4x4-no-slippery 8 months ago
results.json

118 Bytes Upload q-learning trained agent for FrozenLake-v1-4x4-no-slippery 8 months ago