diff --git a/training/runs/webots_n3.log b/training/runs/webots_n3.log
new file mode 100644
index 0000000..cd3ef43
--- /dev/null
+++ b/training/runs/webots_n3.log
@@ -0,0 +1,81 @@
+Config loaded from config.json
+Config: {'W_PER_SHEEP': 2.0, 'W_ALIGN': 0.05, 'W_PEN_BONUS': 10.0, 'W_COMPLETE': 100.0, 'W_STEP_COST': 0.02, 'W_SOUTH': 0.01, 'W_COMPACT': 0.0, 'W_WALL_TOUCH': 0.0, 'WALL_TOUCH_BUFFER': 0.4, 'ALIGN_SHAPE': 'standoff', 'ALIGN_GATED': True, 'ENTRY_AWARE': True, 'ent_coef': 0.02}
+Run dir: runs/webots_n3
+Curriculum: 1 → 3 sheep, 1,500,000 steps/stage
+
+
+[Stage n_sheep=1] training 1,500,000 steps
+           ... [1 sheep | 100,000 steps | ret(last 41)=-22.59  win_sr=15%  cum_sr=15%]
+           ... [1 sheep | 200,000 steps | ret(last 50)=-24.68  win_sr=12%  cum_sr=13%]
+           ... [1 sheep | 300,000 steps | ret(last 50)=-23.63  win_sr=10%  cum_sr=11%]
+           ... [1 sheep | 400,000 steps | ret(last 50)=-18.18  win_sr=12%  cum_sr=12%]
+           ... [1 sheep | 500,000 steps | ret(last 50)=+18.15  win_sr=100%  cum_sr=37%]
+           ... [1 sheep | 600,000 steps | ret(last 50)=+14.43  win_sr=100%  cum_sr=69%]
+           ... [1 sheep | 700,000 steps | ret(last 50)=+14.09  win_sr=100%  cum_sr=81%]
+           ... [1 sheep | 800,000 steps | ret(last 50)=+13.60  win_sr=100%  cum_sr=87%]
+           ... [1 sheep | 900,000 steps | ret(last 50)=+13.64  win_sr=100%  cum_sr=90%]
+           ... [1 sheep | 1,000,000 steps | ret(last 50)=+13.70  win_sr=100%  cum_sr=92%]
+           ... [1 sheep | 1,100,000 steps | ret(last 50)=+13.03  win_sr=100%  cum_sr=93%]
+           ... [1 sheep | 1,200,000 steps | ret(last 50)=+13.32  win_sr=100%  cum_sr=94%]
+           ... [1 sheep | 1,300,000 steps | ret(last 50)=+13.19  win_sr=100%  cum_sr=95%]
+           ... [1 sheep | 1,400,000 steps | ret(last 50)=+13.56  win_sr=100%  cum_sr=95%]
+           ... [1 sheep | 1,500,000 steps | ret(last 50)=+13.20  win_sr=100%  cum_sr=96%]
+[Stage n_sheep=1] evaluating 30 eps
+[Stage n_sheep=1] sr=80%  mean_len=687  mean_min_pen=3.7m  mean_act=0.16
+  failure modes: SUCCESS=24  COMPACT_CANT_DRIVE=6
+  reward/step: progress=+0.0388  alignment=+0.0002  south=-0.0022  compact=+0.0000  wall_touch=+0.0000  pen_bonus=+0.0117  step_cost=-0.0200  complete=+0.1165
+
+[Stage n_sheep=2] training 1,500,000 steps
+           ... [2 sheep | 1,507,336 steps | ret(last 0)=+nan  win_sr=nan%  cum_sr=nan%]
+           ... [2 sheep | 1,607,336 steps | ret(last 41)=-9.02  win_sr=2%  cum_sr=2%]
+           ... [2 sheep | 1,707,336 steps | ret(last 50)=-7.70  win_sr=6%  cum_sr=4%]
+           ... [2 sheep | 1,807,336 steps | ret(last 50)=-5.98  win_sr=16%  cum_sr=9%]
+           ... [2 sheep | 1,907,336 steps | ret(last 50)=-6.55  win_sr=16%  cum_sr=10%]
+           ... [2 sheep | 2,007,336 steps | ret(last 50)=-9.51  win_sr=10%  cum_sr=10%]
+           ... [2 sheep | 2,107,336 steps | ret(last 50)=-0.32  win_sr=36%  cum_sr=15%]
+           ... [2 sheep | 2,207,336 steps | ret(last 50)=+7.58  win_sr=76%  cum_sr=28%]
+           ... [2 sheep | 2,307,336 steps | ret(last 50)=+16.41  win_sr=100%  cum_sr=41%]
+           ... [2 sheep | 2,407,336 steps | ret(last 50)=+17.65  win_sr=100%  cum_sr=54%]
+           ... [2 sheep | 2,507,336 steps | ret(last 50)=+18.87  win_sr=100%  cum_sr=63%]
+           ... [2 sheep | 2,607,336 steps | ret(last 50)=+19.68  win_sr=100%  cum_sr=69%]
+           ... [2 sheep | 2,707,336 steps | ret(last 50)=+19.69  win_sr=100%  cum_sr=73%]
+           ... [2 sheep | 2,807,336 steps | ret(last 50)=+19.71  win_sr=100%  cum_sr=77%]
+           ... [2 sheep | 2,907,336 steps | ret(last 50)=+18.49  win_sr=100%  cum_sr=79%]
+           ... [2 sheep | 3,007,336 steps | ret(last 50)=+19.24  win_sr=100%  cum_sr=81%]
+[Stage n_sheep=2] evaluating 30 eps
+[Stage n_sheep=2] sr=100%  mean_len=654  mean_min_pen=3.4m  mean_act=0.87
+  failure modes: SUCCESS=30
+  reward/step: progress=+0.0905  alignment=+0.0136  south=-0.0078  compact=+0.0000  wall_touch=+0.0000  pen_bonus=+0.0306  step_cost=-0.0200  complete=+0.1529
+
+[Stage n_sheep=3] training 1,500,000 steps
+           ... [3 sheep | 3,014,664 steps | ret(last 0)=+nan  win_sr=nan%  cum_sr=nan%]
+           ... [3 sheep | 3,114,664 steps | ret(last 50)=+25.01  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 3,214,664 steps | ret(last 50)=+23.20  win_sr=98%  cum_sr=99%]
+           ... [3 sheep | 3,314,664 steps | ret(last 50)=+24.99  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 3,414,664 steps | ret(last 50)=+24.87  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 3,514,664 steps | ret(last 50)=+24.74  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 3,614,664 steps | ret(last 50)=+21.31  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 3,714,664 steps | ret(last 50)=+22.95  win_sr=98%  cum_sr=100%]
+           ... [3 sheep | 3,814,664 steps | ret(last 50)=+23.87  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 3,914,664 steps | ret(last 50)=+23.55  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 4,014,664 steps | ret(last 50)=+26.08  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 4,114,664 steps | ret(last 50)=+24.06  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 4,214,664 steps | ret(last 50)=+24.43  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 4,314,664 steps | ret(last 50)=+21.18  win_sr=96%  cum_sr=100%]
+           ... [3 sheep | 4,414,664 steps | ret(last 50)=+23.24  win_sr=100%  cum_sr=100%]
+           ... [3 sheep | 4,514,664 steps | ret(last 50)=+23.97  win_sr=100%  cum_sr=100%]
+[Stage n_sheep=3] evaluating 30 eps
+[Stage n_sheep=3] sr=73%  mean_len=1270  mean_min_pen=1.8m  mean_act=1.12
+  failure modes: SUCCESS=22  PARTIAL_1of3=8
+  reward/step: progress=+0.0685  alignment=+0.0103  south=-0.0295  compact=+0.0000  wall_touch=+0.0000  pen_bonus=+0.0194  step_cost=-0.0200  complete=+0.0578
+
+======================================================================
+  TRAINING SUMMARY
+======================================================================
+  n_sheep=1  sr= 80%  len=  687  min_pen=  3.7m  act=0.16
+  n_sheep=2  sr=100%  len=  654  min_pen=  3.4m  act=0.87
+  n_sheep=3  sr= 73%  len= 1270  min_pen=  1.8m  act=1.12
+
+  Total time: 23.6 min
+  Artefacts:  runs/webots_n3/
+  Plots:      runs/webots_n3/success_rate.png, runs/webots_n3/eval/
diff --git a/training/runs/webots_n3/config.json b/training/runs/webots_n3/config.json
new file mode 100644
index 0000000..a2a98c3
--- /dev/null
+++ b/training/runs/webots_n3/config.json
@@ -0,0 +1,15 @@
+{
+  "W_PER_SHEEP": 2.0,
+  "W_ALIGN": 0.05,
+  "W_PEN_BONUS": 10.0,
+  "W_COMPLETE": 100.0,
+  "W_STEP_COST": 0.02,
+  "W_SOUTH": 0.01,
+  "W_COMPACT": 0.0,
+  "W_WALL_TOUCH": 0.0,
+  "WALL_TOUCH_BUFFER": 0.4,
+  "ALIGN_SHAPE": "standoff",
+  "ALIGN_GATED": true,
+  "ENTRY_AWARE": true,
+  "ent_coef": 0.02
+}
\ No newline at end of file
diff --git a/training/runs/webots_n3/eval/ep_1s_fail.gif b/training/runs/webots_n3/eval/ep_1s_fail.gif
new file mode 100644
index 0000000..cf7aa57
Binary files /dev/null and b/training/runs/webots_n3/eval/ep_1s_fail.gif differ
diff --git a/training/runs/webots_n3/eval/ep_2s_success.gif b/training/runs/webots_n3/eval/ep_2s_success.gif
new file mode 100644
index 0000000..9a757d4
Binary files /dev/null and b/training/runs/webots_n3/eval/ep_2s_success.gif differ
diff --git a/training/runs/webots_n3/eval/ep_3s_success.gif b/training/runs/webots_n3/eval/ep_3s_success.gif
new file mode 100644
index 0000000..7a8b62d
Binary files /dev/null and b/training/runs/webots_n3/eval/ep_3s_success.gif differ
diff --git a/training/runs/webots_n3/eval/traj_1s_fail.png b/training/runs/webots_n3/eval/traj_1s_fail.png
new file mode 100644
index 0000000..7be1651
Binary files /dev/null and b/training/runs/webots_n3/eval/traj_1s_fail.png differ
diff --git a/training/runs/webots_n3/eval/traj_2s_success.png b/training/runs/webots_n3/eval/traj_2s_success.png
new file mode 100644
index 0000000..67e047d
Binary files /dev/null and b/training/runs/webots_n3/eval/traj_2s_success.png differ
diff --git a/training/runs/webots_n3/eval/traj_3s_success.png b/training/runs/webots_n3/eval/traj_3s_success.png
new file mode 100644
index 0000000..595811c
Binary files /dev/null and b/training/runs/webots_n3/eval/traj_3s_success.png differ
diff --git a/training/runs/webots_n3/eval/ts_1s_fail.png b/training/runs/webots_n3/eval/ts_1s_fail.png
new file mode 100644
index 0000000..8fb7e39
Binary files /dev/null and b/training/runs/webots_n3/eval/ts_1s_fail.png differ
diff --git a/training/runs/webots_n3/eval/ts_2s_success.png b/training/runs/webots_n3/eval/ts_2s_success.png
new file mode 100644
index 0000000..8bd4df2
Binary files /dev/null and b/training/runs/webots_n3/eval/ts_2s_success.png differ
diff --git a/training/runs/webots_n3/eval/ts_3s_success.png b/training/runs/webots_n3/eval/ts_3s_success.png
new file mode 100644
index 0000000..48765ea
Binary files /dev/null and b/training/runs/webots_n3/eval/ts_3s_success.png differ
diff --git a/training/runs/webots_n3/final_model.zip b/training/runs/webots_n3/final_model.zip
new file mode 100644
index 0000000..139a531
Binary files /dev/null and b/training/runs/webots_n3/final_model.zip differ
diff --git a/training/runs/webots_n3/stage_results.json b/training/runs/webots_n3/stage_results.json
new file mode 100644
index 0000000..41472df
--- /dev/null
+++ b/training/runs/webots_n3/stage_results.json
@@ -0,0 +1,64 @@
+[
+  {
+    "sr": 0.8,
+    "mean_len": 686.6666666666666,
+    "mean_min_pen": 3.6629639943440755,
+    "mean_act": 0.16181865727591677,
+    "failure_modes": {
+      "SUCCESS": 24,
+      "COMPACT_CANT_DRIVE": 6
+    },
+    "reward_per_step": {
+      "progress": 0.03881567865085689,
+      "alignment": 0.00015139903442241512,
+      "south": -0.00216557193820928,
+      "compact": 0.0,
+      "wall_touch": 0.0,
+      "pen_bonus": 0.011650485436893204,
+      "step_cost": -0.019999999999995886,
+      "complete": 0.11650485436893204
+    },
+    "n_sheep": 1
+  },
+  {
+    "sr": 1.0,
+    "mean_len": 654.0,
+    "mean_min_pen": 3.4076531132062278,
+    "mean_act": 0.8715365563710358,
+    "failure_modes": {
+      "SUCCESS": 30
+    },
+    "reward_per_step": {
+      "progress": 0.09053953751754566,
+      "alignment": 0.01356517500879768,
+      "south": -0.007814150244939332,
+      "compact": 0.0,
+      "wall_touch": 0.0,
+      "pen_bonus": 0.03058103975535168,
+      "step_cost": -0.01999999999999659,
+      "complete": 0.1529051987767584
+    },
+    "n_sheep": 2
+  },
+  {
+    "sr": 0.7333333333333333,
+    "mean_len": 1269.6333333333334,
+    "mean_min_pen": 1.7831791202227274,
+    "mean_act": 1.1211744887920247,
+    "failure_modes": {
+      "SUCCESS": 22,
+      "PARTIAL_1of3": 8
+    },
+    "reward_per_step": {
+      "progress": 0.06853864337494794,
+      "alignment": 0.010319892308307451,
+      "south": -0.029485590403771442,
+      "compact": 0.0,
+      "wall_touch": 0.0,
+      "pen_bonus": 0.01942818136469847,
+      "step_cost": -0.019999999999989426,
+      "complete": 0.05775945811126572
+    },
+    "n_sheep": 3
+  }
+]
\ No newline at end of file
diff --git a/training/runs/webots_n3/success_rate.png b/training/runs/webots_n3/success_rate.png
new file mode 100644
index 0000000..6422772
Binary files /dev/null and b/training/runs/webots_n3/success_rate.png differ
diff --git a/training/runs/webots_n3/vecnorm.pkl b/training/runs/webots_n3/vecnorm.pkl
new file mode 100644
index 0000000..695f22c
Binary files /dev/null and b/training/runs/webots_n3/vecnorm.pkl differ