ssuleiman
/

simrig-orbit-reach

Reinforcement Learning

Model card Files Files and versions

simrig-orbit-reach

209 kB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

ssuleiman's picture

v2: same weights, env preview_episode for simrig preview

add7371 verified about 1 month ago

.gitattributes

1.57 kB
Add orbit-arm reach PPO reference checkpoint (v1) about 1 month ago
README.md

2.81 kB
v2: same weights, env preview_episode for simrig preview about 1 month ago
config.json

12.4 kB
v2: same weights, env preview_episode for simrig preview about 1 month ago
evaluation.json

3.53 kB
Add orbit-arm reach PPO reference checkpoint (v1) about 1 month ago
final_metrics.json

2.29 kB
Add orbit-arm reach PPO reference checkpoint (v1) about 1 month ago
orbit_arm.xml

1.73 kB
Add orbit-arm reach PPO reference checkpoint (v1) about 1 month ago
orbit_reach.py

17.7 kB
v2: same weights, env preview_episode for simrig preview about 1 month ago
policy.params
Detected Pickle imports (7)
- "numpy.ndarray",
- "jax._src.array._reconstruct_array",
- "brax.training.acme.running_statistics.RunningStatisticsState",
- "numpy._core.multiarray._reconstruct",
- "brax.training.types.UInt64",
- "brax.training.acme.running_statistics.NormalizationMode",
- "numpy.dtype"
How to fix it?
156 kB
xet

Add orbit-arm reach PPO reference checkpoint (v1) about 1 month ago
policy_task.v2.frozen.json

10.7 kB
Add orbit-arm reach PPO reference checkpoint (v1) about 1 month ago