jalf/TIR_PROJ
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Sheep training flock of 10 fix?

Browse Source
This commit is contained in:
Johnny Fernandes
2026-04-24 18:06:22 +01:00
parent 65d881aa0f
commit fc961e651c
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
training/smoke_test.py
+5 -5
View File
@@ -160,7 +160,7 @@ SHEEP_COLORS = ["#e41a1c","#377eb8","#4daf4a","#984ea3","#ff7f00",
def _save_smoke_vis(model, vn, n_sheep, save_dir, seed=42, max_steps=2000): def _save_smoke_vis(model, vn, n_sheep, save_dir, seed=42, max_steps=2000):
"""Run one episode and save trajectory + timeseries PNGs.""" """Run one episode and save trajectory + timeseries PNGs."""
from copy import deepcopy from copy import deepcopy
raw = DummyVecEnv([make_env(n_sheep, max_steps, seed)]) raw = DummyVecEnv([make_env(n_sheep, seed=seed, max_steps=max_steps)])
env = VecNormalize(raw, norm_obs=True, norm_reward=False, training=False) env = VecNormalize(raw, norm_obs=True, norm_reward=False, training=False)
env.obs_rms = deepcopy(vn.obs_rms) env.obs_rms = deepcopy(vn.obs_rms)
env.ret_rms = deepcopy(vn.ret_rms) env.ret_rms = deepcopy(vn.ret_rms)
@@ -241,10 +241,10 @@ def main():
p.add_argument("--render", action="store_true") p.add_argument("--render", action="store_true")
args = p.parse_args() args = p.parse_args()
# 1 sheep (500k): sanity check — obs/reward structurally correct? # 1 sheep (500k): hard check — obs/reward structurally correct?
# 2 sheep (1M): first multi-agent step — gradual transfer # 2 sheep (1M): soft check — proves multi-sheep learning has started
# 3 sheep (1.5M): real multi-sheep test at curriculum pace # 3 sheep (1.5M): directional check — not expected to fully converge here
stages = [(1, args.steps, 0.60), (2, args.steps * 2, 0.40), (3, args.steps * 3, 0.35)] stages = [(1, args.steps, 0.60), (2, args.steps * 2, 0.20), (3, args.steps * 3, 0.10)]
model, vn = None, None model, vn = None, None
all_passed = True all_passed = True