{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8700988292694092, "min": 1.8700988292694092, "max": 3.295753002166748, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37820.87890625, "min": 24672.630859375, "max": 150897.5625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.4811320754717, "min": 39.967213114754095, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19708.0, "min": 15064.0, "max": 27916.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1597.737497674885, "min": 1199.9771334302864, "max": 1597.737497674885, "count": 486 }, "SoccerTwos.Self-play.ELO.sum": { "value": 338720.3495070756, "min": 2400.4631656037986, "max": 379875.8964168029, "count": 486 }, "SoccerTwos.Step.mean": { "value": 4999914.0, "min": 9980.0, "max": 4999914.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999914.0, "min": 9980.0, "max": 4999914.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02873898483812809, "min": -0.10513824969530106, "max": 0.17450928688049316, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.063925743103027, "min": -19.9420108795166, "max": 24.678964614868164, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02994154952466488, "min": -0.1047244593501091, "max": 0.17646732926368713, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.317667007446289, "min": -20.840167999267578, "max": 24.9876708984375, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.01920378999122511, "min": -0.631578947368421, "max": 0.4256228600229536, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.0519996881484985, "min": -52.351199984550476, "max": 50.92179983854294, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.01920378999122511, "min": -0.631578947368421, "max": 0.4256228600229536, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.0519996881484985, "min": -52.351199984550476, "max": 50.92179983854294, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016084134335202786, "min": 0.01000754886190407, "max": 0.024137182723886024, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016084134335202786, "min": 0.01000754886190407, "max": 0.024137182723886024, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10967138409614563, "min": 0.00010499681508614837, "max": 0.11730341464281083, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10967138409614563, "min": 0.00010499681508614837, "max": 0.11730341464281083, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11196163892745972, "min": 0.00010591759055387229, "max": 0.12087150886654854, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11196163892745972, "min": 0.00010591759055387229, "max": 0.12087150886654854, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689808656", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "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": "1689813487" }, "total": 4830.369840984, "count": 1, "self": 0.1677002939977683, "children": { "run_training.setup": { "total": 0.008510141000442673, "count": 1, "self": 0.008510141000442673 }, "TrainerController.start_learning": { "total": 4830.193630549002, "count": 1, "self": 4.295788931449351, "children": { "TrainerController._reset_env": { "total": 3.0721712700324133, "count": 25, "self": 3.0721712700324133 }, "TrainerController.advance": { "total": 4822.658342429517, "count": 339801, "self": 3.9652985607026494, "children": { "env_step": { "total": 3438.6393926086166, "count": 339801, "self": 2587.7817735170393, "children": { "SubprocessEnvManager._take_step": { "total": 848.2348908918575, "count": 339801, "self": 23.944038431567606, "children": { "TorchPolicy.evaluate": { "total": 824.2908524602899, "count": 632342, "self": 824.2908524602899 } } }, "workers": { "total": 2.622728199719859, "count": 339801, "self": 0.0, "children": { "worker_root": { "total": 4824.33143751225, "count": 339801, "is_parallel": true, "self": 2717.224129579714, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016139149956870824, "count": 2, "is_parallel": true, "self": 0.0005800950093544088, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010338199863326736, "count": 8, "is_parallel": true, "self": 0.0010338199863326736 } } }, "UnityEnvironment.step": { "total": 0.014475203002803028, "count": 1, "is_parallel": true, "self": 0.000361960002919659, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003173540026182309, "count": 1, "is_parallel": true, "self": 0.0003173540026182309 }, "communicator.exchange": { "total": 0.012671557000430766, "count": 1, "is_parallel": true, "self": 0.012671557000430766 }, "steps_from_proto": { "total": 0.0011243319968343712, "count": 2, "is_parallel": true, "self": 0.0002327539841644466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008915780126699246, "count": 8, "is_parallel": true, "self": 0.0008915780126699246 } } } } } } }, "UnityEnvironment.step": { "total": 2107.0740649625513, "count": 339800, "is_parallel": true, "self": 128.00429471890675, "children": { "UnityEnvironment._generate_step_input": { "total": 87.17355650067475, "count": 339800, "is_parallel": true, "self": 87.17355650067475 }, "communicator.exchange": { "total": 1505.6371768408208, "count": 339800, "is_parallel": true, "self": 1505.6371768408208 }, "steps_from_proto": { "total": 386.2590369021491, "count": 679600, "is_parallel": true, "self": 73.62846255295153, "children": { "_process_rank_one_or_two_observation": { "total": 312.63057434919756, "count": 2718400, "is_parallel": true, "self": 312.63057434919756 } } } } }, "steps_from_proto": { "total": 0.033242969984712545, "count": 48, "is_parallel": true, "self": 0.006481821008492261, "children": { "_process_rank_one_or_two_observation": { "total": 0.026761148976220284, "count": 192, "is_parallel": true, "self": 0.026761148976220284 } } } } } } } } }, "trainer_advance": { "total": 1380.0536512601975, "count": 339801, "self": 35.37263698402239, "children": { "process_trajectory": { "total": 442.39681883015874, "count": 339801, "self": 440.756553943138, "children": { "RLTrainer._checkpoint": { "total": 1.6402648870207486, "count": 10, "self": 1.6402648870207486 } } }, "_update_policy": { "total": 902.2841954460164, "count": 240, "self": 484.9813328000673, "children": { "TorchPOCAOptimizer.update": { "total": 417.30286264594906, "count": 7200, "self": 417.30286264594906 } } } } } } }, "trainer_threads": { "total": 6.410045898519456e-07, "count": 1, "self": 6.410045898519456e-07 }, "TrainerController._save_models": { "total": 0.16732727699854877, "count": 1, "self": 0.0011759909975808114, "children": { "RLTrainer._checkpoint": { "total": 0.16615128600096796, "count": 1, "self": 0.16615128600096796 } } } } } } }