{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7094011306762695, "min": 1.7060964107513428, "max": 3.2957077026367188, "count": 2023 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32929.90234375, "min": 15063.271484375, "max": 120539.0625, "count": 2023 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 83.73684210526316, "min": 53.108695652173914, "max": 999.0, "count": 2023 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19092.0, "min": 15984.0, "max": 24340.0, "count": 2023 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1835.59794116842, "min": 1195.0898768441, "max": 1871.8334763601015, "count": 2008 }, "SoccerTwos.Self-play.ELO.sum": { "value": 209258.16529319988, "min": 2390.1797536882, "max": 326788.4384653412, "count": 2008 }, "SoccerTwos.Step.mean": { "value": 20229980.0, "min": 9186.0, "max": 20229980.0, "count": 2023 }, "SoccerTwos.Step.sum": { "value": 20229980.0, "min": 9186.0, "max": 20229980.0, "count": 2023 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.012247542850673199, "min": -0.1365581601858139, "max": 0.23330456018447876, "count": 2023 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.3962198495864868, "min": -17.777332305908203, "max": 24.496978759765625, "count": 2023 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.007227103225886822, "min": -0.13396771252155304, "max": 0.2343074381351471, "count": 2023 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.8238897919654846, "min": -17.952308654785156, "max": 24.60228157043457, "count": 2023 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2023 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2023 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0463192996225859, "min": -0.6875, "max": 0.6529000017630018, "count": 2023 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.2804001569747925, "min": -56.13800001144409, "max": 60.06680016219616, "count": 2023 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0463192996225859, "min": -0.6875, "max": 0.6529000017630018, "count": 2023 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.2804001569747925, "min": -56.13800001144409, "max": 60.06680016219616, "count": 2023 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2023 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2023 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018102163961157203, "min": 0.0132930524693802, "max": 0.027636111750034616, "count": 977 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018102163961157203, "min": 0.0132930524693802, "max": 0.027636111750034616, "count": 977 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09319581717252731, "min": 0.00011887511456734501, "max": 0.09997177183628082, "count": 977 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09319581717252731, "min": 0.00011887511456734501, "max": 0.09997177183628082, "count": 977 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09598625540733337, "min": 0.00011651071356027386, "max": 0.10465286076068878, "count": 977 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09598625540733337, "min": 0.00011651071356027386, "max": 0.10465286076068878, "count": 977 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 5.7457640847479984e-05, "min": 5.7457640847479984e-05, "max": 0.00029971336809554396, "count": 977 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 5.7457640847479984e-05, "min": 5.7457640847479984e-05, "max": 0.00029971336809554396, "count": 977 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.09999999999999998, "min": 0.09999999999999995, "max": 0.09999999999999998, "count": 977 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.09999999999999998, "min": 0.09999999999999995, "max": 0.09999999999999998, "count": 977 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0019233367479999993, "min": 0.0019233367479999993, "max": 0.0099904551544, "count": 977 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0019233367479999993, "min": 0.0019233367479999993, "max": 0.0099904551544, "count": 977 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709936427", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/enrique/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710099131" }, "total": 162703.539806775, "count": 1, "self": 0.31158212400623597, "children": { "run_training.setup": { "total": 0.05082440100159147, "count": 1, "self": 0.05082440100159147 }, "TrainerController.start_learning": { "total": 162703.17740025, "count": 1, "self": 40.48205535064335, "children": { "TrainerController._reset_env": { "total": 5.344374503987638, "count": 68, "self": 5.344374503987638 }, "TrainerController.advance": { "total": 162656.51332770838, "count": 1359947, "self": 42.57524030187051, "children": { "env_step": { "total": 37096.59710621641, "count": 1359947, "self": 28301.237613603942, "children": { "SubprocessEnvManager._take_step": { "total": 8767.100591769664, "count": 1359947, "self": 296.2759109505132, "children": { "TorchPolicy.evaluate": { "total": 8470.82468081915, "count": 2541172, "self": 8470.82468081915 } } }, "workers": { "total": 28.258900842803996, "count": 1359947, "self": 0.0, "children": { "worker_root": { "total": 162523.00043489703, "count": 1359947, "is_parallel": true, "self": 140079.8256054942, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007015269002295099, "count": 2, "is_parallel": true, "self": 0.0012277070090931375, "children": { "_process_rank_one_or_two_observation": { "total": 0.005787561993201962, "count": 8, "is_parallel": true, "self": 0.005787561993201962 } } }, "UnityEnvironment.step": { "total": 0.041026735001651105, "count": 1, "is_parallel": true, "self": 0.0021334450029826257, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009433890008949675, "count": 1, "is_parallel": true, "self": 0.0009433890008949675 }, "communicator.exchange": { "total": 0.032108987998071825, "count": 1, "is_parallel": true, "self": 0.032108987998071825 }, "steps_from_proto": { "total": 0.005840912999701686, "count": 2, "is_parallel": true, "self": 0.00066583799343789, "children": { "_process_rank_one_or_two_observation": { "total": 0.005175075006263796, "count": 8, "is_parallel": true, "self": 0.005175075006263796 } } } } } } }, "UnityEnvironment.step": { "total": 22442.77061272976, "count": 1359946, "is_parallel": true, "self": 1569.7824730957254, "children": { "UnityEnvironment._generate_step_input": { "total": 1046.919520610416, "count": 1359946, "is_parallel": true, "self": 1046.919520610416 }, "communicator.exchange": { "total": 14664.884012488405, "count": 1359946, "is_parallel": true, "self": 14664.884012488405 }, "steps_from_proto": { "total": 5161.184606535215, "count": 2719892, "is_parallel": true, "self": 800.5663092147151, "children": { "_process_rank_one_or_two_observation": { "total": 4360.6182973205, "count": 10879568, "is_parallel": true, "self": 4360.6182973205 } } } } }, "steps_from_proto": { "total": 0.40421667305054143, "count": 134, "is_parallel": true, "self": 0.043180541066249134, "children": { "_process_rank_one_or_two_observation": { "total": 0.3610361319842923, "count": 536, "is_parallel": true, "self": 0.3610361319842923 } } } } } } } } }, "trainer_advance": { "total": 125517.3409811901, "count": 1359947, "self": 301.213410027558, "children": { "process_trajectory": { "total": 9021.327885178609, "count": 1359947, "self": 9001.53991666856, "children": { "RLTrainer._checkpoint": { "total": 19.787968510048813, "count": 40, "self": 19.787968510048813 } } }, "_update_policy": { "total": 116194.79968598393, "count": 978, "self": 11616.859194668563, "children": { "TorchPOCAOptimizer.update": { "total": 104577.94049131537, "count": 48885, "self": 104577.94049131537 } } } } } } }, "trainer_threads": { "total": 1.7829879652708769e-06, "count": 1, "self": 1.7829879652708769e-06 }, "TrainerController._save_models": { "total": 0.8376409039774444, "count": 1, "self": 0.26598130897036754, "children": { "RLTrainer._checkpoint": { "total": 0.5716595950070769, "count": 1, "self": 0.5716595950070769 } } } } } } }