Add JAX PPO league self-play v1

2026-07-05 06:33:22 +09:00
parent 6037b650f3
commit 94e9ac1854
10 changed files with 1482 additions and 1 deletions
@@ -0,0 +1,77 @@
+base_config: configs/jax_ppo/ladder-v2-expert.yaml
+warm_start_checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_013223_jax-ppo-ladder-v2-expert/latest
+
+run:
+  experiment_name: jax-ppo-league-smoke
+  seed: 20260705
+  artifact_root: /mnt/2tbhdd/coolrl-lost-cities-artifacts/league-smoke
+
+league:
+  cycles: 1
+  league_updates_per_cycle: 1
+  snapshot_interval_updates: 1
+  mirror_probability: 0.5
+  uniform_mix: 0.1
+  stalling_anchor_floor: 0.02
+  stalling_anchor_cap: 0.05
+  pool_max_size: 8
+  max_active_pool_members: 7
+  exploiter_member_fraction_cap: 0.3333333333333333
+  wall_clock_hours: 1.0
+  success_exploiter_win_rate: 0.60
+  stagnation_window: 5
+  stagnation_min_delta: 0.02
+
+evaluation:
+  games: 2
+  duplicate: true
+  shuffle_bank_seed: 20260704
+  batch_games: 2
+  recent_snapshot_evals: 1
+
+exploiter:
+  config: configs/jax_ppo/ladder-v2-exploiter.yaml
+  updates: 1
+
+guards:
+  expert_ci_low: -1000.0
+  max_steps_rate: 1.0
+
+tracking:
+  tracked_summary_path: /mnt/2tbhdd/coolrl-lost-cities-artifacts/league-smoke/summary.jsonl
+  report_path: /mnt/2tbhdd/coolrl-lost-cities-artifacts/league-smoke/report.md
+
+anchors:
+  - name: discard_only
+    kind: static
+    policy_name: discard_only
+    anchor: true
+    stalling: true
+  - name: heuristic_balanced
+    kind: static
+    policy_name: heuristic_balanced
+    anchor: true
+  - name: heuristic_cautious
+    kind: static
+    policy_name: heuristic_cautious
+    anchor: true
+    stalling: true
+  - name: heuristic_expert
+    kind: static
+    policy_name: heuristic_expert
+    anchor: true
+  - name: ladder_v2_gate1_discard
+    kind: checkpoint
+    config: configs/jax_ppo/ladder-v2-discard-only.yaml
+    checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_010429_jax-ppo-ladder-v2-discard-only/latest
+    anchor: true
+  - name: ladder_v2_gate2_balanced
+    kind: checkpoint
+    config: configs/jax_ppo/ladder-v2-balanced.yaml
+    checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_011827_jax-ppo-ladder-v2-balanced/latest
+    anchor: true
+  - name: ladder_v2_gate3_expert
+    kind: checkpoint
+    config: configs/jax_ppo/ladder-v2-expert.yaml
+    checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_013223_jax-ppo-ladder-v2-expert/latest
+    anchor: true
@@ -0,0 +1,77 @@
+base_config: configs/jax_ppo/ladder-v2-expert.yaml
+warm_start_checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_013223_jax-ppo-ladder-v2-expert/latest
+
+run:
+  experiment_name: jax-ppo-league-v1
+  seed: 20260705
+  artifact_root: /mnt/2tbhdd/coolrl-lost-cities-artifacts/league
+
+league:
+  cycles: 5
+  league_updates_per_cycle: 500
+  snapshot_interval_updates: 250
+  mirror_probability: 0.5
+  uniform_mix: 0.1
+  stalling_anchor_floor: 0.02
+  stalling_anchor_cap: 0.05
+  pool_max_size: 24
+  max_active_pool_members: 12
+  exploiter_member_fraction_cap: 0.3333333333333333
+  wall_clock_hours: 6.0
+  success_exploiter_win_rate: 0.60
+  stagnation_window: 5
+  stagnation_min_delta: 0.02
+
+evaluation:
+  games: 10000
+  duplicate: true
+  shuffle_bank_seed: 20260704
+  batch_games: 8192
+  recent_snapshot_evals: 3
+
+exploiter:
+  config: configs/jax_ppo/ladder-v2-exploiter.yaml
+  updates: 250
+
+guards:
+  expert_ci_low: 0.0
+  max_steps_rate: 0.02
+
+tracking:
+  tracked_summary_path: docs/reports/league-v1-2026-07-05-summary.jsonl
+  report_path: docs/reports/league-v1-2026-07-05.md
+
+anchors:
+  - name: discard_only
+    kind: static
+    policy_name: discard_only
+    anchor: true
+    stalling: true
+  - name: heuristic_balanced
+    kind: static
+    policy_name: heuristic_balanced
+    anchor: true
+  - name: heuristic_cautious
+    kind: static
+    policy_name: heuristic_cautious
+    anchor: true
+    stalling: true
+  - name: heuristic_expert
+    kind: static
+    policy_name: heuristic_expert
+    anchor: true
+  - name: ladder_v2_gate1_discard
+    kind: checkpoint
+    config: configs/jax_ppo/ladder-v2-discard-only.yaml
+    checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_010429_jax-ppo-ladder-v2-discard-only/latest
+    anchor: true
+  - name: ladder_v2_gate2_balanced
+    kind: checkpoint
+    config: configs/jax_ppo/ladder-v2-balanced.yaml
+    checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_011827_jax-ppo-ladder-v2-balanced/latest
+    anchor: true
+  - name: ladder_v2_gate3_expert
+    kind: checkpoint
+    config: configs/jax_ppo/ladder-v2-expert.yaml
+    checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_013223_jax-ppo-ladder-v2-expert/latest
+    anchor: true