poca-SoccerTwos / run_logs /timers.json
khaleelsyed's picture
First Push
31960ba
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.2637064456939697,
"min": 3.2595221996307373,
"max": 3.2957754135131836,
"count": 15
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 57963.42578125,
"min": 12512.8603515625,
"max": 105464.8125,
"count": 15
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 988.0,
"min": 688.2857142857143,
"max": 999.0,
"count": 15
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19760.0,
"min": 3996.0,
"max": 31968.0,
"count": 15
},
"SoccerTwos.Step.mean": {
"value": 149617.0,
"min": 9000.0,
"max": 149617.0,
"count": 15
},
"SoccerTwos.Step.sum": {
"value": 149617.0,
"min": 9000.0,
"max": 149617.0,
"count": 15
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.019907740876078606,
"min": 0.019907740876078606,
"max": 0.06816476583480835,
"count": 15
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 0.19907741248607635,
"min": 0.19907741248607635,
"max": 1.0906362533569336,
"count": 15
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.01982649601995945,
"min": 0.01982649601995945,
"max": 0.06819769740104675,
"count": 15
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.1982649564743042,
"min": 0.1982649564743042,
"max": 1.0910978317260742,
"count": 15
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 15
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 15
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.09450000002980233,
"min": -0.42857142857142855,
"max": 0.1294909119606018,
"count": 15
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -0.9450000002980232,
"min": -6.0,
"max": 1.4244000315666199,
"count": 15
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.09450000002980233,
"min": -0.42857142857142855,
"max": 0.1294909119606018,
"count": 15
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -0.9450000002980232,
"min": -6.0,
"max": 1.4244000315666199,
"count": 15
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 15
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 15
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1192.2480612918105,
"min": 1191.7221561177923,
"max": 1200.0,
"count": 12
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 2384.496122583621,
"min": 2384.496122583621,
"max": 9600.0,
"count": 12
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.02130120896617882,
"min": 0.01187217376937042,
"max": 0.02130120896617882,
"count": 6
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.02130120896617882,
"min": 0.01187217376937042,
"max": 0.02130120896617882,
"count": 6
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0016288519138470293,
"min": 0.0002621278157069658,
"max": 0.004079510023196538,
"count": 6
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0016288519138470293,
"min": 0.0002621278157069658,
"max": 0.004079510023196538,
"count": 6
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0016337897677052146,
"min": 0.0002596900444283771,
"max": 0.004125434455151359,
"count": 6
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0016337897677052146,
"min": 0.0002596900444283771,
"max": 0.004125434455151359,
"count": 6
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 6
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 6
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 6
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 6
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 6
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 6
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1702167389",
"python_version": "3.10.11 (main, Apr 20 2023, 19:02:41) [GCC 11.2.0]",
"command_line_arguments": "/home/lab_rat/.local/bin/mlagents-learn /app/data/SoccerTwos.yaml --env=./training-envs-executables/linux/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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702167627"
},
"total": 237.5587633769992,
"count": 1,
"self": 0.005657632997099427,
"children": {
"run_training.setup": {
"total": 0.02983730600135459,
"count": 1,
"self": 0.02983730600135459
},
"TrainerController.start_learning": {
"total": 237.52326843800074,
"count": 1,
"self": 0.20881453799484007,
"children": {
"TrainerController._reset_env": {
"total": 1.1082723340005032,
"count": 1,
"self": 1.1082723340005032
},
"TrainerController.advance": {
"total": 236.07934092000505,
"count": 10201,
"self": 0.1862424469945836,
"children": {
"env_step": {
"total": 194.535413930942,
"count": 10201,
"self": 146.50614589786346,
"children": {
"SubprocessEnvManager._take_step": {
"total": 47.8881980289425,
"count": 10201,
"self": 1.0271327478894818,
"children": {
"TorchPolicy.evaluate": {
"total": 46.861065281053015,
"count": 20262,
"self": 46.861065281053015
}
}
},
"workers": {
"total": 0.1410700041360542,
"count": 10200,
"self": 0.0,
"children": {
"worker_root": {
"total": 237.02311792296132,
"count": 10200,
"is_parallel": true,
"self": 116.07538491899504,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023288359989237506,
"count": 2,
"is_parallel": true,
"self": 0.0004879300013271859,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018409059975965647,
"count": 8,
"is_parallel": true,
"self": 0.0018409059975965647
}
}
},
"UnityEnvironment.step": {
"total": 0.023440058999767643,
"count": 1,
"is_parallel": true,
"self": 0.0006483329998445697,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046868900062690955,
"count": 1,
"is_parallel": true,
"self": 0.00046868900062690955
},
"communicator.exchange": {
"total": 0.020427788998858887,
"count": 1,
"is_parallel": true,
"self": 0.020427788998858887
},
"steps_from_proto": {
"total": 0.0018952480004372774,
"count": 2,
"is_parallel": true,
"self": 0.0003438180028751958,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015514299975620816,
"count": 8,
"is_parallel": true,
"self": 0.0015514299975620816
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 120.94773300396628,
"count": 10199,
"is_parallel": true,
"self": 8.085005178003485,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.044495512036519,
"count": 10199,
"is_parallel": true,
"self": 5.044495512036519
},
"communicator.exchange": {
"total": 85.39343499302777,
"count": 10199,
"is_parallel": true,
"self": 85.39343499302777
},
"steps_from_proto": {
"total": 22.424797320898506,
"count": 20398,
"is_parallel": true,
"self": 3.7809762458673504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.643821075031155,
"count": 81592,
"is_parallel": true,
"self": 18.643821075031155
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 41.357684542068455,
"count": 10200,
"self": 1.6076610940526734,
"children": {
"process_trajectory": {
"total": 13.149435371016807,
"count": 10200,
"self": 13.149435371016807
},
"_update_policy": {
"total": 26.600588076998974,
"count": 6,
"self": 18.501927294004417,
"children": {
"TorchPOCAOptimizer.update": {
"total": 8.098660782994557,
"count": 189,
"self": 8.098660782994557
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1900010576937348e-06,
"count": 1,
"self": 1.1900010576937348e-06
},
"TrainerController._save_models": {
"total": 0.12683945599928848,
"count": 1,
"self": 0.0007181439996202243,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12612131199966825,
"count": 1,
"self": 0.12612131199966825
}
}
}
}
}
}
}