{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.782020092010498, "min": 2.7408828735351562, "max": 3.148832321166992, "count": 149 }, "SoccerTwos.Policy.Entropy.sum": { "value": 53147.7109375, "min": 18819.92578125, "max": 103040.1640625, "count": 149 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 79.75806451612904, "min": 66.62162162162163, "max": 931.6, "count": 149 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19780.0, "min": 16048.0, "max": 33996.0, "count": 149 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1323.1592803467115, "min": 1182.5733001608478, "max": 1323.1592803467115, "count": 149 }, "SoccerTwos.Self-play.ELO.sum": { "value": 164071.75076299222, "min": 2386.5580859722763, "max": 193010.27497535327, "count": 149 }, "SoccerTwos.Step.mean": { "value": 4999933.0, "min": 3499420.0, "max": 4999933.0, "count": 151 }, "SoccerTwos.Step.sum": { "value": 4999933.0, "min": 3499420.0, "max": 4999933.0, "count": 151 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.12314624339342117, "min": -0.03092990815639496, "max": 0.1394692361354828, "count": 151 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 15.270133972167969, "min": -1.051616907119751, "max": 16.178430557250977, "count": 151 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.13183137774467468, "min": -0.036932479590177536, "max": 0.1436532437801361, "count": 151 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 16.347091674804688, "min": -1.2557042837142944, "max": 16.663776397705078, "count": 151 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 151 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 151 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.2843935489654541, "min": -0.5425764716723386, "max": 0.9333999752998352, "count": 151 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 35.26480007171631, "min": -18.76040017604828, "max": 35.26480007171631, "count": 151 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.2843935489654541, "min": -0.5425764716723386, "max": 0.9333999752998352, "count": 151 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 35.26480007171631, "min": -18.76040017604828, "max": 35.26480007171631, "count": 151 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 151 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 151 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01601744956812278, "min": 0.012989187633502297, "max": 0.022939226923820874, "count": 70 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01601744956812278, "min": 0.012989187633502297, "max": 0.022939226923820874, "count": 70 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06345115937292575, "min": 0.0014499741160155584, "max": 0.0641418262074391, "count": 70 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.06345115937292575, "min": 0.0014499741160155584, "max": 0.0641418262074391, "count": 70 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06464051492512227, "min": 0.0014544832248551151, "max": 0.0654796672364076, "count": 70 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.06464051492512227, "min": 0.0014544832248551151, "max": 0.0654796672364076, "count": 70 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 70 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 70 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 70 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 70 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 70 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 70 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682768356", "python_version": "3.8.16 (default, Mar 2 2023, 03:21:46) \n[GCC 11.2.0]", "command_line_arguments": "/root/miniconda3/envs/mlagent_env/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.2+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1682771627" }, "total": 3271.2887740740553, "count": 1, "self": 0.5259581981226802, "children": { "run_training.setup": { "total": 0.02622733684256673, "count": 1, "self": 0.02622733684256673 }, "TrainerController.start_learning": { "total": 3270.73658853909, "count": 1, "self": 2.9680194517131895, "children": { "TrainerController._reset_env": { "total": 7.201641643652692, "count": 9, "self": 7.201641643652692 }, "TrainerController.advance": { "total": 3260.3147750664502, "count": 98240, "self": 3.3056213797535747, "children": { "env_step": { "total": 2625.632222956512, "count": 98240, "self": 1997.8606757714879, "children": { "SubprocessEnvManager._take_step": { "total": 625.7929681187961, "count": 98240, "self": 19.36032558279112, "children": { "TorchPolicy.evaluate": { "total": 606.432642536005, "count": 191892, "self": 606.432642536005 } } }, "workers": { "total": 1.9785790662281215, "count": 98240, "self": 0.0, "children": { "worker_root": { "total": 3263.9388357799035, "count": 98240, "is_parallel": true, "self": 1606.7479629141744, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029094689525663853, "count": 2, "is_parallel": true, "self": 0.0007654514629393816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021440174896270037, "count": 8, "is_parallel": true, "self": 0.0021440174896270037 } } }, "UnityEnvironment.step": { "total": 0.03594986000098288, "count": 1, "is_parallel": true, "self": 0.0006534920539706945, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007200029212981462, "count": 1, "is_parallel": true, "self": 0.0007200029212981462 }, "communicator.exchange": { "total": 0.03261819598264992, "count": 1, "is_parallel": true, "self": 0.03261819598264992 }, "steps_from_proto": { "total": 0.0019581690430641174, "count": 2, "is_parallel": true, "self": 0.00040725315921008587, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015509158838540316, "count": 8, "is_parallel": true, "self": 0.0015509158838540316 } } } } } } }, "steps_from_proto": { "total": 0.016640503890812397, "count": 16, "is_parallel": true, "self": 0.003318921197205782, "children": { "_process_rank_one_or_two_observation": { "total": 0.013321582693606615, "count": 64, "is_parallel": true, "self": 0.013321582693606615 } } }, "UnityEnvironment.step": { "total": 1657.1742323618382, "count": 98239, "is_parallel": true, "self": 69.25188956130296, "children": { "UnityEnvironment._generate_step_input": { "total": 44.359899832634255, "count": 98239, "is_parallel": true, "self": 44.359899832634255 }, "communicator.exchange": { "total": 1348.2308604989666, "count": 98239, "is_parallel": true, "self": 1348.2308604989666 }, "steps_from_proto": { "total": 195.33158246893436, "count": 196478, "is_parallel": true, "self": 39.18618612224236, "children": { "_process_rank_one_or_two_observation": { "total": 156.145396346692, "count": 785912, "is_parallel": true, "self": 156.145396346692 } } } } } } } } } } }, "trainer_advance": { "total": 631.3769307301845, "count": 98240, "self": 24.519971968838945, "children": { "process_trajectory": { "total": 197.50691253738478, "count": 98240, "self": 196.52816882007755, "children": { "RLTrainer._checkpoint": { "total": 0.9787437173072249, "count": 4, "self": 0.9787437173072249 } } }, "_update_policy": { "total": 409.3500462239608, "count": 70, "self": 247.93217604560778, "children": { "TorchPOCAOptimizer.update": { "total": 161.41787017835304, "count": 2115, "self": 161.41787017835304 } } } } } } }, "trainer_threads": { "total": 1.55717134475708e-06, "count": 1, "self": 1.55717134475708e-06 }, "TrainerController._save_models": { "total": 0.25215082010254264, "count": 1, "self": 0.007733169011771679, "children": { "RLTrainer._checkpoint": { "total": 0.24441765109077096, "count": 1, "self": 0.24441765109077096 } } } } } } }