{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5422695875167847, "min": 1.358902931213379, "max": 1.6392451524734497, "count": 131 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30203.806640625, "min": 869.6978759765625, "max": 35354.890625, "count": 131 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.8875, "min": 14.0, "max": 72.31884057971014, "count": 131 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19804.0, "min": 112.0, "max": 20420.0, "count": 131 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1555.0830582808662, "min": 1503.1061852957882, "max": 1569.937910488838, "count": 131 }, "SoccerTwos.Self-play.ELO.sum": { "value": 248813.2893249386, "min": 6140.598878565317, "max": 341490.80077715684, "count": 131 }, "SoccerTwos.Step.mean": { "value": 9999986.0, "min": 8699987.0, "max": 9999986.0, "count": 131 }, "SoccerTwos.Step.sum": { "value": 9999986.0, "min": 8699987.0, "max": 9999986.0, "count": 131 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.039965007454156876, "min": -0.07955111563205719, "max": 0.07412034273147583, "count": 131 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.354435920715332, "min": -15.674731254577637, "max": 12.600458145141602, "count": 131 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04035235196352005, "min": -0.08584316074848175, "max": 0.08051864057779312, "count": 131 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.4160237312316895, "min": -14.986276626586914, "max": 13.688169479370117, "count": 131 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 131 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 131 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.03440125670822911, "min": -0.2702774581192546, "max": 0.3316309686630003, "count": 131 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.469799816608429, "min": -55.96039962768555, "max": 51.402800142765045, "count": 131 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.03440125670822911, "min": -0.2702774581192546, "max": 0.3316309686630003, "count": 131 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.469799816608429, "min": -55.96039962768555, "max": 51.402800142765045, "count": 131 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 131 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 131 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015145652223751919, "min": 0.011791978035277376, "max": 0.023321755667954372, "count": 63 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015145652223751919, "min": 0.011791978035277376, "max": 0.023321755667954372, "count": 63 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10312746713558833, "min": 0.09516235515475273, "max": 0.11794356231888135, "count": 63 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10312746713558833, "min": 0.09516235515475273, "max": 0.11794356231888135, "count": 63 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10443195899327597, "min": 0.09606056759754816, "max": 0.11946648806333542, "count": 63 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10443195899327597, "min": 0.09606056759754816, "max": 0.11946648806333542, "count": 63 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 63 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 63 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 63 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 63 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 63 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 63 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692207371", "python_version": "3.9.17 (main, Jul 5 2023, 16:17:03) \n[Clang 14.0.6 ]", "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1692213584" }, "total": 5904.371516334, "count": 1, "self": 2.3665285830002176, "children": { "run_training.setup": { "total": 0.03477250000000254, "count": 1, "self": 0.03477250000000254 }, "TrainerController.start_learning": { "total": 5901.970215251, "count": 1, "self": 1.335926395909155, "children": { "TrainerController._reset_env": { "total": 6.9797415419994415, "count": 8, "self": 6.9797415419994415 }, "TrainerController.advance": { "total": 5893.388342604091, "count": 90501, "self": 1.1450277041085428, "children": { "env_step": { "total": 1214.93956218408, "count": 90501, "self": 980.8131489869226, "children": { "SubprocessEnvManager._take_step": { "total": 233.3234402870467, "count": 90501, "self": 5.983297622016522, "children": { "TorchPolicy.evaluate": { "total": 227.34014266503019, "count": 163138, "self": 227.34014266503019 } } }, "workers": { "total": 0.802972910110654, "count": 90501, "self": 0.0, "children": { "worker_root": { "total": 5892.433743614063, "count": 90501, "is_parallel": true, "self": 5054.01503899014, "children": { "steps_from_proto": { "total": 0.012321166999555544, "count": 16, "is_parallel": true, "self": 0.00219025000286166, "children": { "_process_rank_one_or_two_observation": { "total": 0.010130916996693884, "count": 64, "is_parallel": true, "self": 0.010130916996693884 } } }, "UnityEnvironment.step": { "total": 838.4063834569233, "count": 90501, "is_parallel": true, "self": 45.301781421703595, "children": { "UnityEnvironment._generate_step_input": { "total": 26.50081490400531, "count": 90501, "is_parallel": true, "self": 26.50081490400531 }, "communicator.exchange": { "total": 647.0776638040975, "count": 90501, "is_parallel": true, "self": 647.0776638040975 }, "steps_from_proto": { "total": 119.52612332711689, "count": 181002, "is_parallel": true, "self": 20.076650796359928, "children": { "_process_rank_one_or_two_observation": { "total": 99.44947253075696, "count": 724008, "is_parallel": true, "self": 99.44947253075696 } } } } } } } } } } }, "trainer_advance": { "total": 4677.303752715903, "count": 90501, "self": 11.050956303944986, "children": { "process_trajectory": { "total": 590.7645311589569, "count": 90501, "self": 589.4128263679576, "children": { "RLTrainer._checkpoint": { "total": 1.3517047909992925, "count": 3, "self": 1.3517047909992925 } } }, "_update_policy": { "total": 4075.4882652530014, "count": 63, "self": 165.5546123100121, "children": { "TorchPOCAOptimizer.update": { "total": 3909.9336529429893, "count": 1890, "self": 3909.9336529429893 } } } } } } }, "trainer_threads": { "total": 5.840001904289238e-07, "count": 1, "self": 5.840001904289238e-07 }, "TrainerController._save_models": { "total": 0.26620412499960366, "count": 1, "self": 0.01405583299947466, "children": { "RLTrainer._checkpoint": { "total": 0.252148292000129, "count": 1, "self": 0.252148292000129 } } } } } } }