Files
coorl-lost-cities/configs/jax_ppo/gates-1-2.yaml
T

45 lines
1.7 KiB
YAML

run:
artifact_root: /mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2
report_path: docs/reports/gates-1-2-2026-07-05.md
summary_path: docs/reports/gates-1-2-2026-07-05-summary.jsonl
shuffle_bank_seed: 20260704
gpu_budget_hours: 8.0
target:
config: /mnt/2tbhdd/coolrl-lost-cities-artifacts/league/2026-07-05_052325_jax-ppo-league-v1/main_ppo_config.json
checkpoint: /mnt/2tbhdd/coolrl-lost-cities-artifacts/league/2026-07-05_052325_jax-ppo-league-v1/snapshots/cycle_01_update_000500
gate1:
games: 2000
batch_games: 8192
delta_games: 200
delta_target_events: 500
delta_pairs: 64
delta_batch_events: 16
gate2:
eval_games: 2000
pass_threshold: 0.55
exploiters:
- name: long_random
config: configs/jax_ppo/gates-1-2-exploiter-long-random.yaml
notes: random init + shaping anneal, extended budget
- name: warmstart_gate3
config: configs/jax_ppo/gates-1-2-exploiter-warmstart.yaml
resume: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_013223_jax-ppo-ladder-v2-expert/latest
notes: ladder v2 gate-3 warm start, shaping disabled
- name: replay_exploiter
config: configs/jax_ppo/gates-1-2-exploiter-replay.yaml
resume: /mnt/2tbhdd/coolrl-lost-cities-artifacts/league/2026-07-05_052325_jax-ppo-league-v1/exploiters/2026-07-05_060727_jax-ppo-league-v1-cycle-1-exploiter/latest
notes: league v1 exploiter warm start, shaping disabled
repair:
max_cycles: 3
league_template: configs/jax_ppo/league-v1.yaml
experiment_name: jax-ppo-gates-1-2-repair
artifact_subdir: gate2c
evaluation_games: 2000
evaluation_batch_games: 8192
guard_expert_ci_low: 0.0
guard_max_steps_rate: 0.02