{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.6018446683883667, "min": 0.5827111601829529, "max": 0.8120706081390381, "count": 3670 }, "SoccerTwos.Policy.Entropy.sum": { "value": 12884.291015625, "min": 7745.21044921875, "max": 29359.546875, "count": 3670 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 68.12328767123287, "min": 35.93333333333333, "max": 110.28888888888889, "count": 3670 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19892.0, "min": 13260.0, "max": 22052.0, "count": 3670 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1809.5697448810472, "min": 1755.8484767966363, "max": 1855.9967198104127, "count": 3670 }, "SoccerTwos.Self-play.ELO.sum": { "value": 264197.1827526329, "min": 161038.07449903816, "max": 495215.8063339108, "count": 3670 }, "SoccerTwos.Step.mean": { "value": 153869994.0, "min": 117179978.0, "max": 153869994.0, "count": 3670 }, "SoccerTwos.Step.sum": { "value": 153869994.0, "min": 117179978.0, "max": 153869994.0, "count": 3670 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04436693340539932, "min": -0.12997154891490936, "max": 0.0677822008728981, "count": 3670 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.4332051277160645, "min": -20.40274429321289, "max": 8.947250366210938, "count": 3670 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0457809753715992, "min": -0.131537526845932, "max": 0.06851954758167267, "count": 3670 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.638241291046143, "min": -20.374248504638672, "max": 9.044580459594727, "count": 3670 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3670 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3670 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.13384551755313215, "min": -0.45234260870062787, "max": 0.45765454570452374, "count": 3670 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.407600045204163, "min": -65.810800075531, "max": 60.41040003299713, "count": 3670 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.13384551755313215, "min": -0.45234260870062787, "max": 0.45765454570452374, "count": 3670 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.407600045204163, "min": -65.810800075531, "max": 60.41040003299713, "count": 3670 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3670 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3670 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.008117538812803105, "min": 0.005019895810983143, "max": 0.012203344982117415, "count": 447 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.008117538812803105, "min": 0.005019895810983143, "max": 0.012203344982117415, "count": 447 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09657069345315297, "min": 0.08678545653820038, "max": 0.1060536672671636, "count": 447 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09657069345315297, "min": 0.08678545653820038, "max": 0.1060536672671636, "count": 447 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09693029448390007, "min": 0.08713594724734625, "max": 0.10640265569090843, "count": 447 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09693029448390007, "min": 0.08713594724734625, "max": 0.10640265569090843, "count": 447 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 6.921219192929501e-05, "min": 6.921219192929501e-05, "max": 0.00012411649962785302, "count": 447 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 6.921219192929501e-05, "min": 6.921219192929501e-05, "max": 0.00012411649962785302, "count": 447 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 447 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 447 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0011612281794999998, "min": 0.0011612281794999998, "max": 0.002074470135300001, "count": 447 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0011612281794999998, "min": 0.0011612281794999998, "max": 0.002074470135300001, "count": 447 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681575967", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/data/qyh/env/ml-agents/bin/mlagents-learn ./results2/SoccerTwos/configuration.yaml", "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": "1681627991" }, "total": 52024.01188302785, "count": 1, "self": 0.06600537849590182, "children": { "run_training.setup": { "total": 0.057591927237808704, "count": 1, "self": 0.057591927237808704 }, "TrainerController.start_learning": { "total": 52023.88828572212, "count": 1, "self": 32.658423255197704, "children": { "TrainerController._reset_env": { "total": 35.529824036639184, "count": 185, "self": 35.529824036639184 }, "TrainerController.advance": { "total": 51955.18101471895, "count": 568029, "self": 24.895031684078276, "children": { "env_step": { "total": 27869.541548587848, "count": 568029, "self": 8625.78939419752, "children": { "SubprocessEnvManager._take_step": { "total": 19215.38568448322, "count": 2603407, "self": 480.9063208703883, "children": { "TorchPolicy.evaluate": { "total": 18734.47936361283, "count": 4780934, "self": 18734.47936361283 } } }, "workers": { "total": 28.366469907108694, "count": 568029, "self": 0.0, "children": { "worker_root": { "total": 442847.7860362842, "count": 2602813, "is_parallel": true, "self": 385774.796314307, "children": { "run_training.setup": { "total": 0.46073541790246964, "count": 8, "is_parallel": true, "self": 0.3072330658324063, "children": { "steps_from_proto": { "total": 0.017542241141200066, "count": 6, "is_parallel": true, "self": 0.003933876287192106, "children": { "_process_rank_one_or_two_observation": { "total": 0.01360836485400796, "count": 24, "is_parallel": true, "self": 0.01360836485400796 } } }, "UnityEnvironment.step": { "total": 0.1359601109288633, "count": 3, "is_parallel": true, "self": 0.0035129161551594734, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0031845159828662872, "count": 3, "is_parallel": true, "self": 0.0031845159828662872 }, "communicator.exchange": { "total": 0.11919922847300768, "count": 3, "is_parallel": true, "self": 0.11919922847300768 }, "steps_from_proto": { "total": 0.010063450317829847, "count": 6, "is_parallel": true, "self": 0.0021319156512618065, "children": { "_process_rank_one_or_two_observation": { "total": 0.00793153466656804, "count": 24, "is_parallel": true, "self": 0.00793153466656804 } } } } } } }, "steps_from_proto": { "total": 6.425742077641189, "count": 2944, "is_parallel": true, "self": 1.1729354937560856, "children": { "_process_rank_one_or_two_observation": { "total": 5.2528065838851035, "count": 11776, "is_parallel": true, "self": 5.2528065838851035 } } }, "UnityEnvironment.step": { "total": 57066.10324448161, "count": 2602802, "is_parallel": true, "self": 3845.151647065766, "children": { "UnityEnvironment._generate_step_input": { "total": 2380.9195000436157, "count": 2602802, "is_parallel": true, "self": 2380.9195000436157 }, "communicator.exchange": { "total": 40571.13893018197, "count": 2602802, "is_parallel": true, "self": 40571.13893018197 }, "steps_from_proto": { "total": 10268.893167190254, "count": 5205604, "is_parallel": true, "self": 1981.577226538211, "children": { "_process_rank_one_or_two_observation": { "total": 8287.315940652043, "count": 20822416, "is_parallel": true, "self": 8287.315940652043 } } } } }, "TrainerController.start_learning": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "TrainerController._reset_env": { "total": 63.74951070919633, "count": 104, "is_parallel": true, "self": 63.74951070919633 }, "TrainerController.advance": { "total": 26928.832347735763, "count": 284616, "is_parallel": true, "self": 12.295898992568254, "children": { "env_step": { "total": 14613.998140137643, "count": 284616, "is_parallel": true, "self": 4405.428603302222, "children": { "SubprocessEnvManager._take_step": { "total": 10193.452210761607, "count": 1339904, "is_parallel": true, "self": 253.24052944034338, "children": { "TorchPolicy.evaluate": { "total": 9940.211681321263, "count": 2463200, "is_parallel": true, "self": 9940.211681321263 } } }, "workers": { "total": 14.654233936220407, "count": 284616, "is_parallel": true, "self": 0.0, "children": { "worker_root": { "total": 215679.11466323212, "count": 1339536, "is_parallel": true, "self": 187270.21099139377, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.14033792912960052, "count": 48, "is_parallel": true, "self": 0.03147101029753685, "children": { "_process_rank_one_or_two_observation": { "total": 0.10886691883206367, "count": 192, "is_parallel": true, "self": 0.10886691883206367 } } }, "UnityEnvironment.step": { "total": 1.0876808874309063, "count": 24, "is_parallel": true, "self": 0.028103329241275787, "children": { "UnityEnvironment._generate_step_input": { "total": 0.025476127862930298, "count": 24, "is_parallel": true, "self": 0.025476127862930298 }, "communicator.exchange": { "total": 0.9535938277840614, "count": 24, "is_parallel": true, "self": 0.9535938277840614 }, "steps_from_proto": { "total": 0.08050760254263878, "count": 48, "is_parallel": true, "self": 0.017055325210094452, "children": { "_process_rank_one_or_two_observation": { "total": 0.06345227733254433, "count": 192, "is_parallel": true, "self": 0.06345227733254433 } } } } } } }, "steps_from_proto": { "total": 3.224274557083845, "count": 1536, "is_parallel": true, "self": 0.6036845743656158, "children": { "_process_rank_one_or_two_observation": { "total": 2.6205899827182293, "count": 6144, "is_parallel": true, "self": 2.6205899827182293 } } }, "UnityEnvironment.step": { "total": 28405.67939728126, "count": 1339512, "is_parallel": true, "self": 1698.1418446823955, "children": { "UnityEnvironment._generate_step_input": { "total": 1196.4171861484647, "count": 1339512, "is_parallel": true, "self": 1196.4171861484647 }, "communicator.exchange": { "total": 20583.621382161975, "count": 1339512, "is_parallel": true, "self": 20583.621382161975 }, "steps_from_proto": { "total": 4927.498984288424, "count": 2679024, "is_parallel": true, "self": 970.6593494638801, "children": { "_process_rank_one_or_two_observation": { "total": 3956.839634824544, "count": 10716096, "is_parallel": true, "self": 3956.839634824544 } } } } } } } } }, "steps_from_proto": { "total": 0.06240393267944455, "count": 16, "is_parallel": true, "self": 0.012195379473268986, "children": { "_process_rank_one_or_two_observation": { "total": 0.050208553206175566, "count": 64, "is_parallel": true, "self": 0.050208553206175566 } } }, "UnityEnvironment.step": { "total": 0.40068820491433144, "count": 8, "is_parallel": true, "self": 0.02000714698806405, "children": { "UnityEnvironment._generate_step_input": { "total": 0.011553495656698942, "count": 8, "is_parallel": true, "self": 0.011553495656698942 }, "communicator.exchange": { "total": 0.33477857476100326, "count": 8, "is_parallel": true, "self": 0.33477857476100326 }, "steps_from_proto": { "total": 0.03434898750856519, "count": 16, "is_parallel": true, "self": 0.0064005679450929165, "children": { "_process_rank_one_or_two_observation": { "total": 0.02794841956347227, "count": 64, "is_parallel": true, "self": 0.02794841956347227 } } } } } } }, "trainer_advance": { "total": 12302.538308605552, "count": 284616, "is_parallel": true, "self": 239.68896805495024, "children": { "process_trajectory": { "total": 5315.9884302690625, "count": 284616, "is_parallel": true, "self": 5298.733270164579, "children": { "RLTrainer._checkpoint": { "total": 17.255160104483366, "count": 40, "is_parallel": true, "self": 17.255160104483366 } } }, "_update_policy": { "total": 6746.860910281539, "count": 224, "is_parallel": true, "self": 4750.593492981046, "children": { "TorchPOCAOptimizer.update": { "total": 1996.2674173004925, "count": 6720, "is_parallel": true, "self": 1996.2674173004925 } } } } } } } } } } } } } } }, "trainer_advance": { "total": 24060.744434447028, "count": 568028, "self": 479.9666658011265, "children": { "process_trajectory": { "total": 10218.523722819053, "count": 568028, "self": 10188.153453873005, "children": { "RLTrainer._checkpoint": { "total": 30.370268946047872, "count": 73, "self": 30.370268946047872 } } }, "_update_policy": { "total": 13362.254045826849, "count": 447, "self": 9413.401890929788, "children": { "TorchPOCAOptimizer.update": { "total": 3948.8521548970602, "count": 13410, "self": 3948.8521548970602 } } } } } } }, "trainer_threads": { "total": 2.3460015654563904e-06, "count": 1, "self": 2.3460015654563904e-06 }, "TrainerController._save_models": { "total": 0.5190213653258979, "count": 1, "self": 0.004309995099902153, "children": { "RLTrainer._checkpoint": { "total": 0.5147113702259958, "count": 1, "self": 0.5147113702259958 } } } } } } }