{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9940828084945679, "min": 1.9250413179397583, "max": 3.295696258544922, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39371.171875, "min": 18072.1640625, "max": 105462.25, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.56521739130435, "min": 46.86666666666667, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19712.0, "min": 15420.0, "max": 26748.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1588.3377596889718, "min": 1189.6239736413738, "max": 1588.9025155039476, "count": 492 }, "SoccerTwos.Self-play.ELO.sum": { "value": 292254.1477827708, "min": 2379.2479472827476, "max": 323884.13112812873, "count": 492 }, "SoccerTwos.Step.mean": { "value": 4999990.0, "min": 9390.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999990.0, "min": 9390.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.046051863580942154, "min": -0.09800790250301361, "max": 0.1445728838443756, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 8.473543167114258, "min": -16.857358932495117, "max": 20.354021072387695, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04870099574327469, "min": -0.10557367652654648, "max": 0.1461763232946396, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 8.960983276367188, "min": -18.158672332763672, "max": 21.41598129272461, "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": 0.04942826181650162, "min": -0.5882352941176471, "max": 0.5074642832790103, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 9.094800174236298, "min": -46.91200029850006, "max": 53.57719969749451, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04942826181650162, "min": -0.5882352941176471, "max": 0.5074642832790103, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 9.094800174236298, "min": -46.91200029850006, "max": 53.57719969749451, "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": 0.012337295606266707, "min": 0.011238514065917115, "max": 0.0242387202316119, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012337295606266707, "min": 0.011238514065917115, "max": 0.0242387202316119, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.16405876179536183, "min": 0.0001077352852007607, "max": 0.19100076059500376, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.16405876179536183, "min": 0.0001077352852007607, "max": 0.19100076059500376, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.16573583881060283, "min": 0.00010417407793283928, "max": 0.19399343480666478, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.16573583881060283, "min": 0.00010417407793283928, "max": 0.19399343480666478, "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": "1683534335", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/simon/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "2.0.1", "numpy_version": "1.24.3", "end_time_seconds": "1683542828" }, "total": 8492.131372958, "count": 1, "self": 6.214209418998507, "children": { "run_training.setup": { "total": 0.012205337000523286, "count": 1, "self": 0.012205337000523286 }, "TrainerController.start_learning": { "total": 8485.904958202002, "count": 1, "self": 6.274196070773542, "children": { "TrainerController._reset_env": { "total": 2.3137918390057166, "count": 20, "self": 2.3137918390057166 }, "TrainerController.advance": { "total": 8477.14530233122, "count": 337426, "self": 5.866904899114161, "children": { "env_step": { "total": 6640.1098586133385, "count": 337426, "self": 4121.219354358957, "children": { "SubprocessEnvManager._take_step": { "total": 2515.416214833812, "count": 337426, "self": 32.983176036530494, "children": { "TorchPolicy.evaluate": { "total": 2482.4330387972814, "count": 630086, "self": 2482.4330387972814 } } }, "workers": { "total": 3.474289420569221, "count": 337426, "self": 0.0, "children": { "worker_root": { "total": 8470.344369069873, "count": 337426, "is_parallel": true, "self": 4938.9767666343405, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016166470004463918, "count": 2, "is_parallel": true, "self": 0.00045937100185255986, "children": { "_process_rank_one_or_two_observation": { "total": 0.001157275998593832, "count": 8, "is_parallel": true, "self": 0.001157275998593832 } } }, "UnityEnvironment.step": { "total": 0.020554523000100744, "count": 1, "is_parallel": true, "self": 0.0004304829981265357, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030222000077628763, "count": 1, "is_parallel": true, "self": 0.00030222000077628763 }, "communicator.exchange": { "total": 0.01866418800000247, "count": 1, "is_parallel": true, "self": 0.01866418800000247 }, "steps_from_proto": { "total": 0.0011576320011954522, "count": 2, "is_parallel": true, "self": 0.00024029399901337456, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009173380021820776, "count": 8, "is_parallel": true, "self": 0.0009173380021820776 } } } } } } }, "UnityEnvironment.step": { "total": 3531.3487634385338, "count": 337425, "is_parallel": true, "self": 124.21453258204201, "children": { "UnityEnvironment._generate_step_input": { "total": 65.76661410034012, "count": 337425, "is_parallel": true, "self": 65.76661410034012 }, "communicator.exchange": { "total": 3027.6263491545797, "count": 337425, "is_parallel": true, "self": 3027.6263491545797 }, "steps_from_proto": { "total": 313.74126760157196, "count": 674850, "is_parallel": true, "self": 60.21671261635038, "children": { "_process_rank_one_or_two_observation": { "total": 253.52455498522158, "count": 2699400, "is_parallel": true, "self": 253.52455498522158 } } } } }, "steps_from_proto": { "total": 0.01883899699896574, "count": 38, "is_parallel": true, "self": 0.003705121989696636, "children": { "_process_rank_one_or_two_observation": { "total": 0.015133875009269104, "count": 152, "is_parallel": true, "self": 0.015133875009269104 } } } } } } } } }, "trainer_advance": { "total": 1831.1685388187689, "count": 337426, "self": 41.4889978363326, "children": { "process_trajectory": { "total": 989.53945726446, "count": 337426, "self": 987.8054899424615, "children": { "RLTrainer._checkpoint": { "total": 1.7339673219985343, "count": 10, "self": 1.7339673219985343 } } }, "_update_policy": { "total": 800.1400837179763, "count": 240, "self": 332.10756031706387, "children": { "TorchPOCAOptimizer.update": { "total": 468.0325234009124, "count": 7200, "self": 468.0325234009124 } } } } } } }, "trainer_threads": { "total": 6.040008884156123e-07, "count": 1, "self": 6.040008884156123e-07 }, "TrainerController._save_models": { "total": 0.17166735700084246, "count": 1, "self": 0.004591200999129796, "children": { "RLTrainer._checkpoint": { "total": 0.16707615600171266, "count": 1, "self": 0.16707615600171266 } } } } } } }