{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4032293558120728, "min": 1.335113525390625, "max": 3.2957358360290527, "count": 4999 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28827.943359375, "min": 16326.2392578125, "max": 132883.015625, "count": 4999 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.36842105263158, "min": 42.017699115044245, "max": 999.0, "count": 4999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19568.0, "min": 12464.0, "max": 31968.0, "count": 4999 }, "SoccerTwos.Step.mean": { "value": 49999837.0, "min": 9000.0, "max": 49999837.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999837.0, "min": 9000.0, "max": 49999837.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.005748743191361427, "min": -0.16800421476364136, "max": 0.15263666212558746, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.8738089799880981, "min": -25.766983032226562, "max": 26.063232421875, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0035653365775942802, "min": -0.16701161861419678, "max": 0.1564570665359497, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.54193115234375, "min": -25.923744201660156, "max": 24.64728546142578, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.017406578910978215, "min": -0.6923076923076923, "max": 0.549299999590843, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.645799994468689, "min": -71.9348002076149, "max": 56.54180043935776, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.017406578910978215, "min": -0.6923076923076923, "max": 0.549299999590843, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.645799994468689, "min": -71.9348002076149, "max": 56.54180043935776, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1653.402986118717, "min": 1184.9540952187335, "max": 1657.4334998334316, "count": 4989 }, "SoccerTwos.Self-play.ELO.sum": { "value": 251317.253890045, "min": 2369.908190437467, "max": 370950.81130859273, "count": 4989 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014911050900506477, "min": 0.009855329223986095, "max": 0.02534129578756013, "count": 2422 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014911050900506477, "min": 0.009855329223986095, "max": 0.02534129578756013, "count": 2422 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11463145092129708, "min": 7.451118945027702e-05, "max": 0.12258531252543131, "count": 2422 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11463145092129708, "min": 7.451118945027702e-05, "max": 0.12258531252543131, "count": 2422 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1156033140917619, "min": 8.000898681833253e-05, "max": 0.12473117758830389, "count": 2422 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1156033140917619, "min": 8.000898681833253e-05, "max": 0.12473117758830389, "count": 2422 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2422 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2422 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 2422 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 2422 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2422 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2422 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725432822", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/opt/homebrew/Caskroom/miniconda/base/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0", "numpy_version": "1.23.5", "end_time_seconds": "1725575282" }, "total": 142458.34137191717, "count": 1, "self": 0.18699249997735023, "children": { "run_training.setup": { "total": 0.014624916948378086, "count": 1, "self": 0.014624916948378086 }, "TrainerController.start_learning": { "total": 142458.13975450024, "count": 1, "self": 28.19141752179712, "children": { "TrainerController._reset_env": { "total": 11.047923249658197, "count": 250, "self": 11.047923249658197 }, "TrainerController.advance": { "total": 142418.81520447833, "count": 3427684, "self": 26.96817143401131, "children": { "env_step": { "total": 114470.66904603597, "count": 3427684, "self": 110344.05174450623, "children": { "SubprocessEnvManager._take_step": { "total": 4104.1215292685665, "count": 3427684, "self": 123.97406195709482, "children": { "TorchPolicy.evaluate": { "total": 3980.1474673114717, "count": 6280080, "self": 3980.1474673114717 } } }, "workers": { "total": 22.495772261172533, "count": 3427684, "self": 0.0, "children": { "worker_root": { "total": 142411.53307974525, "count": 3427684, "is_parallel": true, "self": 35912.720678471494, "children": { "steps_from_proto": { "total": 0.2789099640212953, "count": 500, "is_parallel": true, "self": 0.03130230400711298, "children": { "_process_rank_one_or_two_observation": { "total": 0.24760766001418233, "count": 2000, "is_parallel": true, "self": 0.24760766001418233 } } }, "UnityEnvironment.step": { "total": 106498.53349130973, "count": 3427684, "is_parallel": true, "self": 276.2459207624197, "children": { "UnityEnvironment._generate_step_input": { "total": 1936.5180972204544, "count": 3427684, "is_parallel": true, "self": 1936.5180972204544 }, "communicator.exchange": { "total": 100733.32693901518, "count": 3427684, "is_parallel": true, "self": 100733.32693901518 }, "steps_from_proto": { "total": 3552.4425343116745, "count": 6855368, "is_parallel": true, "self": 394.96940548857674, "children": { "_process_rank_one_or_two_observation": { "total": 3157.473128823098, "count": 27421472, "is_parallel": true, "self": 3157.473128823098 } } } } } } } } } } }, "trainer_advance": { "total": 27921.177987008356, "count": 3427684, "self": 257.7169491527602, "children": { "process_trajectory": { "total": 5863.179171543568, "count": 3427684, "self": 5854.6805919976905, "children": { "RLTrainer._checkpoint": { "total": 8.498579545877874, "count": 100, "self": 8.498579545877874 } } }, "_update_policy": { "total": 21800.281866312027, "count": 2422, "self": 2380.0092728282325, "children": { "TorchPOCAOptimizer.update": { "total": 19420.272593483794, "count": 72681, "self": 19420.272593483794 } } } } } } }, "trainer_threads": { "total": 2.915039658546448e-07, "count": 1, "self": 2.915039658546448e-07 }, "TrainerController._save_models": { "total": 0.08520895894616842, "count": 1, "self": 0.000859375111758709, "children": { "RLTrainer._checkpoint": { "total": 0.08434958383440971, "count": 1, "self": 0.08434958383440971 } } } } } } }