{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8764951229095459, "min": 0.8624724745750427, "max": 2.85634708404541, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8368.775390625, "min": 8368.775390625, "max": 29251.8515625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.824334144592285, "min": 0.29758745431900024, "max": 12.824334144592285, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2500.7451171875, "min": 57.73196792602539, "max": 2582.002197265625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06571180834897164, "min": 0.0655404469973434, "max": 0.07591333174530197, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26284723339588656, "min": 0.2621617879893736, "max": 0.3702124786436531, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21399488672614098, "min": 0.10645972287359959, "max": 0.2539002905873692, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8559795469045639, "min": 0.42583889149439835, "max": 1.2695014529368458, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.75, "min": 3.1136363636363638, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 137.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.1136363636363638, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 137.0, "max": 1400.0, "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 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674657249", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674657669" }, "total": 420.950544969, "count": 1, "self": 0.3912014630000158, "children": { "run_training.setup": { "total": 0.09905496700002914, "count": 1, "self": 0.09905496700002914 }, "TrainerController.start_learning": { "total": 420.460288539, "count": 1, "self": 0.5283445460012217, "children": { "TrainerController._reset_env": { "total": 9.848483746, "count": 1, "self": 9.848483746 }, "TrainerController.advance": { "total": 409.9632042609988, "count": 18201, "self": 0.30126310400174816, "children": { "env_step": { "total": 409.66194115699705, "count": 18201, "self": 269.58716646700054, "children": { "SubprocessEnvManager._take_step": { "total": 139.80428554099478, "count": 18201, "self": 1.3327606539966155, "children": { "TorchPolicy.evaluate": { "total": 138.47152488699817, "count": 18201, "self": 30.186083503998077, "children": { "TorchPolicy.sample_actions": { "total": 108.28544138300009, "count": 18201, "self": 108.28544138300009 } } } } }, "workers": { "total": 0.27048914900171894, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 419.27561059299273, "count": 18201, "is_parallel": true, "self": 201.951132492996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005355174999976953, "count": 1, "is_parallel": true, "self": 0.003167522000012468, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021876529999644845, "count": 10, "is_parallel": true, "self": 0.0021876529999644845 } } }, "UnityEnvironment.step": { "total": 0.0327959089999581, "count": 1, "is_parallel": true, "self": 0.00038614400006053984, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023106199995481802, "count": 1, "is_parallel": true, "self": 0.00023106199995481802 }, "communicator.exchange": { "total": 0.030716696999945725, "count": 1, "is_parallel": true, "self": 0.030716696999945725 }, "steps_from_proto": { "total": 0.001462005999997018, "count": 1, "is_parallel": true, "self": 0.00036271599987003356, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010992900001269845, "count": 10, "is_parallel": true, "self": 0.0010992900001269845 } } } } } } }, "UnityEnvironment.step": { "total": 217.32447809999672, "count": 18200, "is_parallel": true, "self": 8.149935276978795, "children": { "UnityEnvironment._generate_step_input": { "total": 4.836805258006791, "count": 18200, "is_parallel": true, "self": 4.836805258006791 }, "communicator.exchange": { "total": 175.63322205200285, "count": 18200, "is_parallel": true, "self": 175.63322205200285 }, "steps_from_proto": { "total": 28.70451551300829, "count": 18200, "is_parallel": true, "self": 6.236005695002007, "children": { "_process_rank_one_or_two_observation": { "total": 22.468509818006282, "count": 182000, "is_parallel": true, "self": 22.468509818006282 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.851700000723213e-05, "count": 1, "self": 3.851700000723213e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 407.28857979900516, "count": 336903, "is_parallel": true, "self": 8.576417619018684, "children": { "process_trajectory": { "total": 233.35586488098636, "count": 336903, "is_parallel": true, "self": 232.68096938698648, "children": { "RLTrainer._checkpoint": { "total": 0.6748954939998839, "count": 4, "is_parallel": true, "self": 0.6748954939998839 } } }, "_update_policy": { "total": 165.35629729900012, "count": 90, "is_parallel": true, "self": 41.252959024001086, "children": { "TorchPPOOptimizer.update": { "total": 124.10333827499903, "count": 4587, "is_parallel": true, "self": 124.10333827499903 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12021746899995378, "count": 1, "self": 0.0008173999999598891, "children": { "RLTrainer._checkpoint": { "total": 0.11940006899999389, "count": 1, "self": 0.11940006899999389 } } } } } } }