550 kB

Ctrl+K

card: modes vs conflicts — K* = number of conflict classes (8/8/9 modes -> 1/2/3 regions)

ac21c4a verified 4 days ago

.gitattributes

1.64 kB
Add landing videos (mp4 + gif) and record_video.py; embed in model card 4 days ago
LICENSE

1.08 kB
14-parameter linear policy for LunarLander-v3 (mean 264.1, 60/60, 0.35% crashes) 4 days ago
README.md

5.4 kB
card: modes vs conflicts — K* = number of conflict classes (8/8/9 modes -> 1/2/3 regions) 4 days ago
config.json

813 Bytes
14-parameter linear policy for LunarLander-v3 (mean 264.1, 60/60, 0.35% crashes) 4 days ago
lunarlander-14params.gif

136 kB
xet

Add landing videos (mp4 + gif) and record_video.py; embed in model card 4 days ago
lunarlander-14params.mp4

395 kB
xet

Landing video from three different seeds (40122/42940/51305) 4 days ago
model.py

3.1 kB
14-parameter linear policy for LunarLander-v3 (mean 264.1, 60/60, 0.35% crashes) 4 days ago
model.safetensors

128 Bytes
xet

14-parameter linear policy for LunarLander-v3 (mean 264.1, 60/60, 0.35% crashes) 4 days ago
record_video.py

3.01 kB
Landing video from three different seeds (40122/42940/51305) 4 days ago
requirements.txt

120 Bytes
14-parameter linear policy for LunarLander-v3 (mean 264.1, 60/60, 0.35% crashes) 4 days ago
verify.py

3.57 kB
14-parameter linear policy for LunarLander-v3 (mean 264.1, 60/60, 0.35% crashes) 4 days ago