poca-SoccerTwos / run_logs /timers.json
Armageddon
1M steps
f5c3bb2 verified
raw
history blame
20.2 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.581103801727295,
"min": 2.5516366958618164,
"max": 3.2958099842071533,
"count": 100
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 50961.3125,
"min": 7969.787109375,
"max": 105558.1796875,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 80.2258064516129,
"min": 55.35632183908046,
"max": 999.0,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19896.0,
"min": 3996.0,
"max": 31584.0,
"count": 100
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1352.4757192524328,
"min": 1198.60352483943,
"max": 1367.9394363247825,
"count": 99
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 167706.98918730166,
"min": 2398.5014391117093,
"max": 236106.92457846194,
"count": 99
},
"SoccerTwos.Step.mean": {
"value": 999906.0,
"min": 9808.0,
"max": 999906.0,
"count": 100
},
"SoccerTwos.Step.sum": {
"value": 999906.0,
"min": 9808.0,
"max": 999906.0,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.04702385887503624,
"min": -0.05981454998254776,
"max": 0.2279219925403595,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 5.877982139587402,
"min": -4.067389488220215,
"max": 26.391326904296875,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.04137760028243065,
"min": -0.06182079389691353,
"max": 0.2337680160999298,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 5.1722002029418945,
"min": -4.2038140296936035,
"max": 26.365886688232422,
"count": 100
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 100
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.31638719940185545,
"min": -0.5726000037458208,
"max": 0.4409020433620531,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -39.548399925231934,
"min": -39.548399925231934,
"max": 44.36960029602051,
"count": 100
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.31638719940185545,
"min": -0.5726000037458208,
"max": 0.4409020433620531,
"count": 100
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -39.548399925231934,
"min": -39.548399925231934,
"max": 44.36960029602051,
"count": 100
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.02333000085976285,
"min": 0.0188174694213861,
"max": 0.029864283553130613,
"count": 93
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.02333000085976285,
"min": 0.0188174694213861,
"max": 0.029864283553130613,
"count": 93
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.07346217725425959,
"min": 0.00018049896078247747,
"max": 0.07346217725425959,
"count": 93
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.07346217725425959,
"min": 0.00018049896078247747,
"max": 0.07346217725425959,
"count": 93
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.07889127209782601,
"min": 0.00018250954422965702,
"max": 0.07889127209782601,
"count": 93
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.07889127209782601,
"min": 0.00018250954422965702,
"max": 0.07889127209782601,
"count": 93
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.00010000000000000003,
"min": 0.00010000000000000002,
"max": 0.00010000000000000003,
"count": 93
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.00010000000000000003,
"min": 0.00010000000000000002,
"max": 0.00010000000000000003,
"count": 93
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.30000000000000004,
"min": 0.29999999999999993,
"max": 0.30000000000000004,
"count": 93
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.30000000000000004,
"min": 0.29999999999999993,
"max": 0.30000000000000004,
"count": 93
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.010000000000000002,
"min": 0.009999999999999998,
"max": 0.010000000000000002,
"count": 93
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.010000000000000002,
"min": 0.009999999999999998,
"max": 0.010000000000000002,
"count": 93
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1718188839",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718191438"
},
"total": 2599.619468486,
"count": 1,
"self": 0.43442459800053257,
"children": {
"run_training.setup": {
"total": 0.08677365399989867,
"count": 1,
"self": 0.08677365399989867
},
"TrainerController.start_learning": {
"total": 2599.0982702339998,
"count": 1,
"self": 1.7265686019422901,
"children": {
"TrainerController._reset_env": {
"total": 3.9477936830001,
"count": 5,
"self": 3.9477936830001
},
"TrainerController.advance": {
"total": 2593.1190700510574,
"count": 65530,
"self": 1.8325360030598858,
"children": {
"env_step": {
"total": 1866.413338386987,
"count": 65530,
"self": 1422.788005765017,
"children": {
"SubprocessEnvManager._take_step": {
"total": 442.64046290798706,
"count": 65530,
"self": 12.87198660598051,
"children": {
"TorchPolicy.evaluate": {
"total": 429.76847630200655,
"count": 126672,
"self": 429.76847630200655
}
}
},
"workers": {
"total": 0.9848697139830165,
"count": 65530,
"self": 0.0,
"children": {
"worker_root": {
"total": 2594.193995947025,
"count": 65530,
"is_parallel": true,
"self": 1400.6798708340068,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011166742000114027,
"count": 2,
"is_parallel": true,
"self": 0.005195205999825703,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005971536000288324,
"count": 8,
"is_parallel": true,
"self": 0.005971536000288324
}
}
},
"UnityEnvironment.step": {
"total": 0.043100416000015684,
"count": 1,
"is_parallel": true,
"self": 0.0012577169998166937,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00098445300000094,
"count": 1,
"is_parallel": true,
"self": 0.00098445300000094
},
"communicator.exchange": {
"total": 0.03700466600002983,
"count": 1,
"is_parallel": true,
"self": 0.03700466600002983
},
"steps_from_proto": {
"total": 0.003853580000168222,
"count": 2,
"is_parallel": true,
"self": 0.0007070389999626059,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003146541000205616,
"count": 8,
"is_parallel": true,
"self": 0.003146541000205616
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1193.5039388590194,
"count": 65529,
"is_parallel": true,
"self": 72.23818044697532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 50.718528201010486,
"count": 65529,
"is_parallel": true,
"self": 50.718528201010486
},
"communicator.exchange": {
"total": 836.7790457800047,
"count": 65529,
"is_parallel": true,
"self": 836.7790457800047
},
"steps_from_proto": {
"total": 233.76818443102889,
"count": 131058,
"is_parallel": true,
"self": 38.903030409843495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 194.8651540211854,
"count": 524232,
"is_parallel": true,
"self": 194.8651540211854
}
}
}
}
},
"steps_from_proto": {
"total": 0.010186253998881512,
"count": 8,
"is_parallel": true,
"self": 0.002105531998040533,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008080722000840979,
"count": 32,
"is_parallel": true,
"self": 0.008080722000840979
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 724.8731956610106,
"count": 65530,
"self": 13.854863987046656,
"children": {
"process_trajectory": {
"total": 148.62476898296518,
"count": 65530,
"self": 147.99413865996485,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6306303230003323,
"count": 2,
"self": 0.6306303230003323
}
}
},
"_update_policy": {
"total": 562.3935626909988,
"count": 93,
"self": 304.3529159450052,
"children": {
"TorchPOCAOptimizer.update": {
"total": 258.0406467459936,
"count": 5658,
"self": 258.0406467459936
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.569998837832827e-07,
"count": 1,
"self": 9.569998837832827e-07
},
"TrainerController._save_models": {
"total": 0.3048369409998486,
"count": 1,
"self": 0.0035004579999622365,
"children": {
"RLTrainer._checkpoint": {
"total": 0.30133648299988636,
"count": 1,
"self": 0.30133648299988636
}
}
}
}
}
}
}