20 lines
16 KiB
JSON
20 lines
16 KiB
JSON
{"event": "gate1_tournament", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate1/expert_cap2_vs_expert_cap3.json", "learner": "expert_cap2", "losses": 2102.0, "max_steps_rate": 0.0, "mean_game_length": 46.549, "mean_score_diff": -1.89325, "opened_colors_per_game": 1.77925, "opponent": "expert_cap3", "play_action_rate": 0.2414775169804832, "positive_expeditions_per_game": 0.94175, "score_diff_ci95_high": -1.4203123965597364, "score_diff_ci95_low": -2.366187603440264, "score_diff_std": 15.261096936571331, "ties": 132.0, "wilson_high": 0.45693730157215046, "wilson_low": 0.42617495329274474, "win_rate": 0.4415, "wins": 1766.0}
|
|
{"event": "gate1_tournament", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate1/expert_cap2_vs_expert_capN.json", "learner": "expert_cap2", "losses": 2092.0, "max_steps_rate": 0.0, "mean_game_length": 46.354, "mean_score_diff": -1.88075, "opened_colors_per_game": 1.7815, "opponent": "expert_capN", "play_action_rate": 0.24223387949830538, "positive_expeditions_per_game": 0.93725, "score_diff_ci95_high": -1.4070318876291175, "score_diff_ci95_low": -2.3544681123708826, "score_diff_std": 15.286282970338549, "ties": 130.0, "wilson_high": 0.45994507591745637, "wilson_low": 0.4291614222877006, "win_rate": 0.4445, "wins": 1778.0}
|
|
{"event": "gate1_tournament", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate1/expert_cap3_vs_expert_capN.json", "learner": "expert_cap3", "losses": 1927.0, "max_steps_rate": 0.0, "mean_game_length": 45.35975, "mean_score_diff": 0.0285, "opened_colors_per_game": 2.21525, "opponent": "expert_capN", "play_action_rate": 0.3101634934459303, "positive_expeditions_per_game": 1.20625, "score_diff_ci95_high": 0.5258735279417411, "score_diff_ci95_low": -0.46887352794174114, "score_diff_std": 16.04961324366783, "ties": 137.0, "wilson_high": 0.49949486790031544, "wilson_low": 0.4685358342849551, "win_rate": 0.484, "wins": 1936.0}
|
|
{"event": "gate1_vs_league", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate1/expert_cap2_vs_league_v1_update_500.json", "learner": "expert_cap2", "losses": 2871.0, "max_steps_rate": 0.00025, "mean_game_length": 55.372, "mean_score_diff": -20.88625, "opened_colors_per_game": 1.9735, "opponent": "league_v1_update_500", "play_action_rate": 0.22526015834941476, "positive_expeditions_per_game": 1.09725, "score_diff_ci95_high": -19.787867065349186, "score_diff_ci95_low": -21.984632934650815, "score_diff_std": 35.44342491958145, "ties": 39.0, "wilson_high": 0.2865114339331819, "wilson_low": 0.2589251127636324, "win_rate": 0.2725, "wins": 1090.0}
|
|
{"event": "gate1_vs_league", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate1/expert_cap3_vs_league_v1_update_500.json", "learner": "expert_cap3", "losses": 2590.0, "max_steps_rate": 0.0, "mean_game_length": 53.52525, "mean_score_diff": -14.35125, "opened_colors_per_game": 2.7385, "opponent": "league_v1_update_500", "play_action_rate": 0.320897958422324, "positive_expeditions_per_game": 1.52675, "score_diff_ci95_high": -13.256641796659636, "score_diff_ci95_low": -15.445858203340364, "score_diff_std": 35.32161912528796, "ties": 50.0, "wilson_high": 0.3548273870268761, "wilson_low": 0.32547963482582853, "win_rate": 0.34, "wins": 1360.0}
|
|
{"event": "gate1_vs_league", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate1/expert_capN_vs_league_v1_update_500.json", "learner": "expert_capN", "losses": 2585.0, "max_steps_rate": 0.0, "mean_game_length": 53.29175, "mean_score_diff": -13.967, "opened_colors_per_game": 3.004, "opponent": "league_v1_update_500", "play_action_rate": 0.3410701746172932, "positive_expeditions_per_game": 1.56475, "score_diff_ci95_high": -12.879677994093045, "score_diff_ci95_low": -15.054322005906956, "score_diff_std": 35.086502770569304, "ties": 49.0, "wilson_high": 0.3563415432992672, "wilson_low": 0.3269626002235683, "win_rate": 0.3415, "wins": 1366.0}
|
|
{"ci95_high": 0.3559042062015777, "ci95_low": -0.32834170620157765, "deltas_npy": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate1/delta_open_deltas.npy", "event": "gate1_delta_open", "histogram": {"counts": [107, 1643, 5209, 7192, 10627, 5447, 1662, 113], "edges": [-200.0, -100.0, -50.0, -20.0, 0.0, 20.0, 50.0, 100.0, 200.0]}, "histogram_png": "docs/reports/gates-1-2-delta-open-hist.png", "judgment": "near_zero", "mean_delta": 0.01378125, "pairs": 64, "quantiles": {"max": 149.0, "min": -167.0, "p05": -52.0, "p25": -17.0, "p50": 0.0, "p75": 17.0, "p95": 51.0}, "samples": 32000, "states": 500, "std_delta": 31.225479356323433}
|
|
{"checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_094311_gates-1-2-long-random-exploiter/latest", "event": "gate2_exploiter", "exploiter": "long_random", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_094311_gates-1-2-long-random-exploiter/eval_vs_league_v1_update_500_duplicate.json", "losses": 1610.0, "max_steps_rate": 0.0, "mean_game_length": 50.74375, "mean_score_diff": 10.95125, "notes": "random init + shaping anneal, extended budget", "opened_colors_per_game": 4.99575, "play_action_rate": 0.8010700772505124, "positive_expeditions_per_game": 2.53625, "resume": null, "score_diff_ci95_high": 12.423541316332845, "score_diff_ci95_low": 9.478958683667155, "score_diff_std": 47.50897440589277, "ties": 42.0, "train_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_094311_gates-1-2-long-random-exploiter", "wilson_high": 0.6021679468487495, "wilson_low": 0.5716651100188423, "win_rate": 0.587, "wins": 2348.0}
|
|
{"checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_105902_gates-1-2-warmstart-gate3-exploiter/latest", "event": "gate2_exploiter", "exploiter": "warmstart_gate3", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_105902_gates-1-2-warmstart-gate3-exploiter/eval_vs_league_v1_update_500_duplicate.json", "losses": 1605.0, "max_steps_rate": 0.0, "mean_game_length": 50.8715, "mean_score_diff": 11.38075, "notes": "ladder v2 gate-3 warm start, shaping disabled", "opened_colors_per_game": 4.9945, "play_action_rate": 0.798003736847281, "positive_expeditions_per_game": 2.5195, "resume": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_013223_jax-ppo-ladder-v2-expert/latest", "score_diff_ci95_high": 12.872234578510747, "score_diff_ci95_low": 9.889265421489254, "score_diff_std": 48.128316645747006, "ties": 35.0, "train_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_105902_gates-1-2-warmstart-gate3-exploiter", "wilson_high": 0.6051483732088389, "wilson_low": 0.5746789269990148, "win_rate": 0.59, "wins": 2360.0}
|
|
{"checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_115602_gates-1-2-replay-exploiter/latest", "event": "gate2_exploiter", "exploiter": "replay_exploiter", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_115602_gates-1-2-replay-exploiter/eval_vs_league_v1_update_500_duplicate.json", "losses": 1638.0, "max_steps_rate": 0.0, "mean_game_length": 51.4305, "mean_score_diff": 10.42525, "notes": "league v1 exploiter warm start, shaping disabled", "opened_colors_per_game": 4.99775, "play_action_rate": 0.7904596181514173, "positive_expeditions_per_game": 2.54225, "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", "score_diff_ci95_high": 11.913719629678091, "score_diff_ci95_low": 8.936780370321909, "score_diff_std": 48.0310280688623, "ties": 34.0, "train_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/exploiters/2026-07-05_115602_gates-1-2-replay-exploiter", "wilson_high": 0.5971992743148633, "wilson_low": 0.5666433769856256, "win_rate": 0.582, "wins": 2328.0}
|
|
{"event": "gate2_judgment", "passed": false, "threshold": 0.55, "worst_exploiter": "warmstart_gate3", "worst_win_rate": 0.59}
|
|
{"elapsed_seconds": 11425.08623591601, "event": "gates_complete", "run_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2"}
|
|
{"cycle": 1, "event": "gate2c_league_cycle", "league_config": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/league_config.yaml", "league_run_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01", "target_checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/snapshots/cycle_01_update_000500", "target_config": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/main_ppo_config.json", "worst_protocol": "warmstart_gate3"}
|
|
{"cycle": 1, "event": "gate2c_guard_expert", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/guard_vs_heuristic_expert.json", "losses": 1188.0, "max_steps_rate": 0.0, "mean_game_length": 54.61975, "mean_score_diff": 19.654, "opened_colors_per_game": 4.7015, "passed": true, "play_action_rate": 0.6708126417051431, "positive_expeditions_per_game": 2.1505, "score_diff_ci95_high": 20.81558482366198, "score_diff_ci95_low": 18.49241517633802, "score_diff_std": 37.482869759149246, "target_checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/snapshots/cycle_01_update_000500", "target_config": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/main_ppo_config.json", "ties": 41.0, "wilson_high": 0.7068566468456556, "wilson_low": 0.6782734877661645, "win_rate": 0.69275, "wins": 2771.0}
|
|
{"checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_143807_gates-1-2-long-random-exploiter/latest", "cycle": 1, "event": "gate2c_exploiter", "exploiter": "long_random", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_143807_gates-1-2-long-random-exploiter/eval_vs_repair_cycle_01_duplicate.json", "losses": 1810.0, "max_steps_rate": 0.0, "mean_game_length": 51.4185, "mean_score_diff": 6.27925, "notes": "random init + shaping anneal, extended budget", "opened_colors_per_game": 4.99425, "play_action_rate": 0.7816023796562719, "positive_expeditions_per_game": 2.52, "resume": null, "score_diff_ci95_high": 7.76660187726116, "score_diff_ci95_low": 4.79189812273884, "score_diff_std": 47.99495961530356, "target_checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/snapshots/cycle_01_update_000500", "target_config": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/main_ppo_config.json", "target_name": "repair_cycle_01", "ties": 34.0, "train_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_143807_gates-1-2-long-random-exploiter", "wilson_high": 0.5544028831760525, "wilson_low": 0.5235222802473508, "win_rate": 0.539, "wins": 2156.0}
|
|
{"checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_155430_gates-1-2-warmstart-gate3-exploiter/latest", "cycle": 1, "event": "gate2c_exploiter", "exploiter": "warmstart_gate3", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_155430_gates-1-2-warmstart-gate3-exploiter/eval_vs_repair_cycle_01_duplicate.json", "losses": 1763.0, "max_steps_rate": 0.0, "mean_game_length": 50.434, "mean_score_diff": 7.0285, "notes": "ladder v2 gate-3 warm start, shaping disabled", "opened_colors_per_game": 4.9935, "play_action_rate": 0.8006960073764884, "positive_expeditions_per_game": 2.4845, "resume": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2/2026-07-05_013223_jax-ppo-ladder-v2-expert/latest", "score_diff_ci95_high": 8.490821414519859, "score_diff_ci95_low": 5.5661785854801415, "score_diff_std": 47.18725831288327, "target_checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/snapshots/cycle_01_update_000500", "target_config": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/main_ppo_config.json", "target_name": "repair_cycle_01", "ties": 41.0, "train_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_155430_gates-1-2-warmstart-gate3-exploiter", "wilson_high": 0.5643659496573598, "wilson_low": 0.5335400249002497, "win_rate": 0.549, "wins": 2196.0}
|
|
{"checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_165151_gates-1-2-replay-exploiter/latest", "cycle": 1, "event": "gate2c_exploiter", "exploiter": "replay_exploiter", "games": 4000, "json": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_165151_gates-1-2-replay-exploiter/eval_vs_repair_cycle_01_duplicate.json", "losses": 1798.0, "max_steps_rate": 0.0, "mean_game_length": 51.116, "mean_score_diff": 6.10225, "notes": "league v1 exploiter warm start, shaping disabled", "opened_colors_per_game": 4.99425, "play_action_rate": 0.7845902569268536, "positive_expeditions_per_game": 2.50025, "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", "score_diff_ci95_high": 7.583110013023179, "score_diff_ci95_low": 4.62138998697682, "score_diff_std": 47.785475385853, "target_checkpoint": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/snapshots/cycle_01_update_000500", "target_config": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/league/2026-07-05_125709_jax-ppo-gates-1-2-repair-c01/main_ppo_config.json", "target_name": "repair_cycle_01", "ties": 45.0, "train_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2/gate2c/cycle_01/battery/2026-07-05_165151_gates-1-2-replay-exploiter", "wilson_high": 0.5546520360903574, "wilson_low": 0.523772647611401, "win_rate": 0.53925, "wins": 2157.0}
|
|
{"cycle": 1, "event": "gate2c_judgment", "passed": true, "threshold": 0.55, "worst_exploiter": "warmstart_gate3", "worst_win_rate": 0.549}
|
|
{"elapsed_seconds_total": 28945.184503759025, "event": "gates_repair_complete", "run_dir": "/mnt/2tbhdd/coolrl-lost-cities-artifacts/gates-1-2/2026-07-05_094238_gates-1-2"}
|