{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8531585931777954, "min": 0.8531585931777954, "max": 2.849118232727051, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8155.3427734375, "min": 4324.96142578125, "max": 28748.00390625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199960.0, "min": 9992.0, "max": 199960.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199960.0, "min": 9992.0, "max": 199960.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.663939476013184, "min": 0.8249726295471191, "max": 12.663939476013184, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2469.46826171875, "min": 16.499452590942383, "max": 2574.77685546875, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07553822325252102, "min": 0.06370287543372707, "max": 0.07553822325252102, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3021528930100841, "min": 0.2555204649901248, "max": 0.3708540599881078, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19784748159787233, "min": 0.17910562882236405, "max": 0.2845899269861334, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7913899263914893, "min": 0.7913899263914893, "max": 1.2944463085310132, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.214097262000005e-06, "min": 8.214097262000005e-06, "max": 0.000277164007612, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.285638904800002e-05, "min": 3.285638904800002e-05, "max": 0.0013858200380599999, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10273800000000001, "min": 0.10273800000000001, "max": 0.192388, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41095200000000004, "min": 0.41095200000000004, "max": 0.96194, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001466262000000001, "min": 0.0001466262000000001, "max": 0.0046201612, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005865048000000004, "min": 0.0005865048000000004, "max": 0.023100806, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.84090909090909, "min": 5.781818181818182, "max": 24.977272727272727, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 311.0, "max": 1373.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 5.781818181818182, "max": 24.977272727272727, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 311.0, "max": 1373.0, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681562252", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681562738" }, "total": 485.960594868, "count": 1, "self": 0.4744572840000387, "children": { "run_training.setup": { "total": 0.1134056799999712, "count": 1, "self": 0.1134056799999712 }, "TrainerController.start_learning": { "total": 485.372731904, "count": 1, "self": 0.5937183789935148, "children": { "TrainerController._reset_env": { "total": 3.991478709999967, "count": 1, "self": 3.991478709999967 }, "TrainerController.advance": { "total": 480.6398949070065, "count": 17402, "self": 0.3091692620120057, "children": { "env_step": { "total": 480.3307256449945, "count": 17402, "self": 351.2745105950102, "children": { "SubprocessEnvManager._take_step": { "total": 128.7550710459829, "count": 17402, "self": 1.9882499359911776, "children": { "TorchPolicy.evaluate": { "total": 126.76682110999172, "count": 17402, "self": 126.76682110999172 } } }, "workers": { "total": 0.30114400400140084, "count": 17402, "self": 0.0, "children": { "worker_root": { "total": 483.77265355400385, "count": 17402, "is_parallel": true, "self": 221.3265434610147, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020873010000173053, "count": 1, "is_parallel": true, "self": 0.0006741129999454643, "children": { "_process_rank_one_or_two_observation": { "total": 0.001413188000071841, "count": 10, "is_parallel": true, "self": 0.001413188000071841 } } }, "UnityEnvironment.step": { "total": 0.11177193100002114, "count": 1, "is_parallel": true, "self": 0.0006438959999854887, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008097030000158156, "count": 1, "is_parallel": true, "self": 0.0008097030000158156 }, "communicator.exchange": { "total": 0.10845002799999293, "count": 1, "is_parallel": true, "self": 0.10845002799999293 }, "steps_from_proto": { "total": 0.0018683040000269102, "count": 1, "is_parallel": true, "self": 0.0003876440001135961, "children": { "_process_rank_one_or_two_observation": { "total": 0.001480659999913314, "count": 10, "is_parallel": true, "self": 0.001480659999913314 } } } } } } }, "UnityEnvironment.step": { "total": 262.44611009298916, "count": 17401, "is_parallel": true, "self": 10.348950656991178, "children": { "UnityEnvironment._generate_step_input": { "total": 5.870127904007518, "count": 17401, "is_parallel": true, "self": 5.870127904007518 }, "communicator.exchange": { "total": 210.43117276799734, "count": 17401, "is_parallel": true, "self": 210.43117276799734 }, "steps_from_proto": { "total": 35.795858763993124, "count": 17401, "is_parallel": true, "self": 7.208681513999693, "children": { "_process_rank_one_or_two_observation": { "total": 28.58717724999343, "count": 174010, "is_parallel": true, "self": 28.58717724999343 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013196899999456946, "count": 1, "self": 0.00013196899999456946, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 476.6854514550191, "count": 431054, "is_parallel": true, "self": 11.155984776013838, "children": { "process_trajectory": { "total": 266.255469939005, "count": 431054, "is_parallel": true, "self": 265.43889210700496, "children": { "RLTrainer._checkpoint": { "total": 0.8165778320000641, "count": 4, "is_parallel": true, "self": 0.8165778320000641 } } }, "_update_policy": { "total": 199.27399674000026, "count": 86, "is_parallel": true, "self": 74.70472814300422, "children": { "TorchPPOOptimizer.update": { "total": 124.56926859699604, "count": 4383, "is_parallel": true, "self": 124.56926859699604 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14750793899997916, "count": 1, "self": 0.00119498999993084, "children": { "RLTrainer._checkpoint": { "total": 0.14631294900004832, "count": 1, "self": 0.14631294900004832 } } } } } } }