kupru's picture
first run
c48e90d
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.5402047634124756,
"min": 2.5402047634124756,
"max": 2.5498669147491455,
"count": 2
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 58607.6015625,
"min": 47733.5078125,
"max": 58607.6015625,
"count": 2
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 55.48863636363637,
"min": 55.48863636363637,
"max": 64.36363636363636,
"count": 2
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19532.0,
"min": 16992.0,
"max": 19532.0,
"count": 2
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1537.4520934807072,
"min": 1534.3935281677052,
"max": 1537.4520934807072,
"count": 2
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 270591.56845260446,
"min": 202539.94571813708,
"max": 270591.56845260446,
"count": 2
},
"SoccerTwos.Step.mean": {
"value": 9779987.0,
"min": 9769992.0,
"max": 9779987.0,
"count": 2
},
"SoccerTwos.Step.sum": {
"value": 9779987.0,
"min": 9769992.0,
"max": 9779987.0,
"count": 2
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.0544770322740078,
"min": -0.0544770322740078,
"max": -0.028912479057908058,
"count": 2
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -9.587957382202148,
"min": -9.587957382202148,
"max": -3.787534713745117,
"count": 2
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.05579162761569023,
"min": -0.05579162761569023,
"max": -0.031879957765340805,
"count": 2
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -9.819326400756836,
"min": -9.819326400756836,
"max": -4.176274299621582,
"count": 2
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 2
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 2
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.048363634808496994,
"min": -0.08014656296213164,
"max": -0.048363634808496994,
"count": 2
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -8.511999726295471,
"min": -10.499199748039246,
"max": -8.511999726295471,
"count": 2
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.048363634808496994,
"min": -0.08014656296213164,
"max": -0.048363634808496994,
"count": 2
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -8.511999726295471,
"min": -10.499199748039246,
"max": -8.511999726295471,
"count": 2
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1696783892",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/home/ana/Projektit/hugging/soccertwos/venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1696783950"
},
"total": 57.42563396994956,
"count": 1,
"self": 0.006208683946169913,
"children": {
"run_training.setup": {
"total": 0.11949111899593845,
"count": 1,
"self": 0.11949111899593845
},
"TrainerController.start_learning": {
"total": 57.29993416700745,
"count": 1,
"self": 0.040766926133073866,
"children": {
"TrainerController._reset_env": {
"total": 5.705403263971675,
"count": 2,
"self": 5.705403263971675
},
"TrainerController.advance": {
"total": 50.94050173991127,
"count": 1530,
"self": 0.034535818558651954,
"children": {
"env_step": {
"total": 34.55547925073188,
"count": 1530,
"self": 27.685120858834125,
"children": {
"SubprocessEnvManager._take_step": {
"total": 6.847566052514594,
"count": 1531,
"self": 0.20769104413921013,
"children": {
"TorchPolicy.evaluate": {
"total": 6.639875008375384,
"count": 2798,
"self": 6.639875008375384
}
}
},
"workers": {
"total": 0.022792339383158833,
"count": 1530,
"self": 0.0,
"children": {
"worker_root": {
"total": 87.61538019235013,
"count": 1530,
"is_parallel": true,
"self": 68.35553965624422,
"children": {
"run_training.setup": {
"total": 0.11949111899593845,
"count": 1,
"is_parallel": true,
"self": 0.08583508693845943,
"children": {
"steps_from_proto": {
"total": 0.005766789021436125,
"count": 2,
"is_parallel": true,
"self": 0.0014531869674101472,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004313602054025978,
"count": 8,
"is_parallel": true,
"self": 0.004313602054025978
}
}
},
"UnityEnvironment.step": {
"total": 0.0278892430360429,
"count": 1,
"is_parallel": true,
"self": 0.0007742461166344583,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0008806539699435234,
"count": 1,
"is_parallel": true,
"self": 0.0008806539699435234
},
"communicator.exchange": {
"total": 0.023792159976437688,
"count": 1,
"is_parallel": true,
"self": 0.023792159976437688
},
"steps_from_proto": {
"total": 0.0024421829730272293,
"count": 2,
"is_parallel": true,
"self": 0.0005407399730756879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019014429999515414,
"count": 8,
"is_parallel": true,
"self": 0.0019014429999515414
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.004452660970855504,
"count": 2,
"is_parallel": true,
"self": 0.0009618738549761474,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003490787115879357,
"count": 8,
"is_parallel": true,
"self": 0.003490787115879357
}
}
},
"UnityEnvironment.step": {
"total": 19.13589675613912,
"count": 1528,
"is_parallel": true,
"self": 1.0241968964110129,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.0250182411400601,
"count": 1528,
"is_parallel": true,
"self": 1.0250182411400601
},
"communicator.exchange": {
"total": 13.89324302377645,
"count": 1528,
"is_parallel": true,
"self": 13.89324302377645
},
"steps_from_proto": {
"total": 3.193438594811596,
"count": 3056,
"is_parallel": true,
"self": 0.7139255938818678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.479513000929728,
"count": 12224,
"is_parallel": true,
"self": 2.479513000929728
}
}
}
}
},
"TrainerController.start_learning": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"TrainerController._reset_env": {
"total": 5.705403263971675,
"count": 2,
"is_parallel": true,
"self": 5.705403263971675
},
"TrainerController.advance": {
"total": 32.185165390896145,
"count": 1235,
"is_parallel": true,
"self": 0.027747171348892152,
"children": {
"env_step": {
"total": 24.84874262235826,
"count": 1235,
"is_parallel": true,
"self": 19.25259252556134,
"children": {
"SubprocessEnvManager._take_step": {
"total": 5.5482283955207095,
"count": 1236,
"is_parallel": true,
"self": 0.16566000110469759,
"children": {
"TorchPolicy.evaluate": {
"total": 5.382568394416012,
"count": 2274,
"is_parallel": true,
"self": 5.382568394416012
}
}
},
"workers": {
"total": 0.01835254131583497,
"count": 1235,
"is_parallel": true,
"self": 0.0,
"children": {
"worker_root": {
"total": 37.98809464479564,
"count": 1235,
"is_parallel": true,
"self": 22.408434155222494,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005766789021436125,
"count": 2,
"is_parallel": true,
"self": 0.0014531869674101472,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004313602054025978,
"count": 8,
"is_parallel": true,
"self": 0.004313602054025978
}
}
},
"UnityEnvironment.step": {
"total": 0.0278892430360429,
"count": 1,
"is_parallel": true,
"self": 0.0007742461166344583,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0008806539699435234,
"count": 1,
"is_parallel": true,
"self": 0.0008806539699435234
},
"communicator.exchange": {
"total": 0.023792159976437688,
"count": 1,
"is_parallel": true,
"self": 0.023792159976437688
},
"steps_from_proto": {
"total": 0.0024421829730272293,
"count": 2,
"is_parallel": true,
"self": 0.0005407399730756879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019014429999515414,
"count": 8,
"is_parallel": true,
"self": 0.0019014429999515414
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.004452660970855504,
"count": 2,
"is_parallel": true,
"self": 0.0009618738549761474,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003490787115879357,
"count": 8,
"is_parallel": true,
"self": 0.003490787115879357
}
}
},
"UnityEnvironment.step": {
"total": 15.575207828602288,
"count": 1234,
"is_parallel": true,
"self": 0.8268890920444392,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.8285353232058696,
"count": 1234,
"is_parallel": true,
"self": 0.8285353232058696
},
"communicator.exchange": {
"total": 11.338853520981502,
"count": 1234,
"is_parallel": true,
"self": 11.338853520981502
},
"steps_from_proto": {
"total": 2.5809298923704773,
"count": 2468,
"is_parallel": true,
"self": 0.5749322547926567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.0059976375778206,
"count": 9872,
"is_parallel": true,
"self": 2.0059976375778206
}
}
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.003886807942762971,
"count": 2,
"is_parallel": true,
"self": 0.0009482309687882662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029385769739747047,
"count": 8,
"is_parallel": true,
"self": 0.0029385769739747047
}
}
},
"UnityEnvironment.step": {
"total": 0.025682352017611265,
"count": 1,
"is_parallel": true,
"self": 0.000759823014959693,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007638870156370103,
"count": 1,
"is_parallel": true,
"self": 0.0007638870156370103
},
"communicator.exchange": {
"total": 0.021930588991381228,
"count": 1,
"is_parallel": true,
"self": 0.021930588991381228
},
"steps_from_proto": {
"total": 0.002228052995633334,
"count": 2,
"is_parallel": true,
"self": 0.0005018569645471871,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017261960310861468,
"count": 8,
"is_parallel": true,
"self": 0.0017261960310861468
}
}
}
}
}
}
},
"trainer_advance": {
"total": 7.308675597188994,
"count": 1235,
"is_parallel": true,
"self": 0.19045817520236596,
"children": {
"process_trajectory": {
"total": 7.118217421986628,
"count": 1235,
"is_parallel": true,
"self": 7.118217421986628
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 16.35048667062074,
"count": 1530,
"self": 0.23428562824847177,
"children": {
"process_trajectory": {
"total": 9.00634833337972,
"count": 1530,
"self": 9.00634833337972
},
"_update_policy": {
"total": 7.109852708992548,
"count": 1,
"self": 1.325621280062478,
"children": {
"TorchPOCAOptimizer.update": {
"total": 5.78423142893007,
"count": 5,
"self": 5.78423142893007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6560079529881477e-06,
"count": 1,
"self": 1.6560079529881477e-06
},
"TrainerController._save_models": {
"total": 0.6132605809834786,
"count": 1,
"self": 0.0025487419916316867,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6107118389918469,
"count": 1,
"self": 0.6107118389918469
}
}
}
}
}
}
}