{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8250987529754639, "min": 0.8250987529754639, "max": 2.83732533454895, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8032.33642578125, "min": 8032.33642578125, "max": 29119.46875, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.080318450927734, "min": 0.44762668013572693, "max": 14.106208801269531, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2886.46533203125, "min": 86.8395767211914, "max": 2886.46533203125, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06977067743449453, "min": 0.06353342460189357, "max": 0.0736068118700453, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3488533871724726, "min": 0.25413369840757427, "max": 0.35727567289061496, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1579944309679901, "min": 0.1443296899252078, "max": 0.28146748658927045, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7899721548399505, "min": 0.5773187597008312, "max": 1.3691867515444756, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000023e-06, "min": 3.0528989824000023e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.526449491200001e-05, "min": 1.526449491200001e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891760000000003, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.4119904000000001, "max": 0.9846880000000001, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.077824000000005e-05, "min": 6.077824000000005e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00030389120000000027, "min": 0.00030389120000000027, "max": 0.024235931200000005, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.763636363636362, "min": 4.590909090909091, "max": 28.022727272727273, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1527.0, "min": 202.0, "max": 1531.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.763636363636362, "min": 4.590909090909091, "max": 28.022727272727273, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1527.0, "min": 202.0, "max": 1531.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680117656", "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 /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "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": "1680119290" }, "total": 1634.4200644360003, "count": 1, "self": 0.37332009300007485, "children": { "run_training.setup": { "total": 0.12031972200020391, "count": 1, "self": 0.12031972200020391 }, "TrainerController.start_learning": { "total": 1633.926424621, "count": 1, "self": 1.207905044056588, "children": { "TrainerController._reset_env": { "total": 6.893835688000308, "count": 1, "self": 6.893835688000308 }, "TrainerController.advance": { "total": 1625.698550199943, "count": 45499, "self": 0.6737013268839291, "children": { "env_step": { "total": 1625.024848873059, "count": 45499, "self": 1318.789030222952, "children": { "SubprocessEnvManager._take_step": { "total": 305.5900266670933, "count": 45499, "self": 5.077906725049161, "children": { "TorchPolicy.evaluate": { "total": 300.51211994204414, "count": 45499, "self": 300.51211994204414 } } }, "workers": { "total": 0.6457919830136234, "count": 45499, "self": 0.0, "children": { "worker_root": { "total": 1630.9105573719426, "count": 45499, "is_parallel": true, "self": 1063.7236828319856, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018819829997482884, "count": 1, "is_parallel": true, "self": 0.0005624149989671423, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013195680007811461, "count": 10, "is_parallel": true, "self": 0.0013195680007811461 } } }, "UnityEnvironment.step": { "total": 0.12093200999970577, "count": 1, "is_parallel": true, "self": 0.003153456000291044, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004014239998468838, "count": 1, "is_parallel": true, "self": 0.0004014239998468838 }, "communicator.exchange": { "total": 0.11538751199987018, "count": 1, "is_parallel": true, "self": 0.11538751199987018 }, "steps_from_proto": { "total": 0.001989617999697657, "count": 1, "is_parallel": true, "self": 0.00042029800033560605, "children": { "_process_rank_one_or_two_observation": { "total": 0.001569319999362051, "count": 10, "is_parallel": true, "self": 0.001569319999362051 } } } } } } }, "UnityEnvironment.step": { "total": 567.186874539957, "count": 45498, "is_parallel": true, "self": 22.638055046035788, "children": { "UnityEnvironment._generate_step_input": { "total": 12.498984581891364, "count": 45498, "is_parallel": true, "self": 12.498984581891364 }, "communicator.exchange": { "total": 459.3451663080218, "count": 45498, "is_parallel": true, "self": 459.3451663080218 }, "steps_from_proto": { "total": 72.70466860400802, "count": 45498, "is_parallel": true, "self": 13.906194310128285, "children": { "_process_rank_one_or_two_observation": { "total": 58.798474293879735, "count": 454980, "is_parallel": true, "self": 58.798474293879735 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011218400004509022, "count": 1, "self": 0.00011218400004509022, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1618.5059237209935, "count": 876449, "is_parallel": true, "self": 21.63062269703005, "children": { "process_trajectory": { "total": 581.0125831989626, "count": 876449, "is_parallel": true, "self": 577.8292616359631, "children": { "RLTrainer._checkpoint": { "total": 3.183321562999481, "count": 10, "is_parallel": true, "self": 3.183321562999481 } } }, "_update_policy": { "total": 1015.8627178250008, "count": 227, "is_parallel": true, "self": 459.4786093919656, "children": { "TorchPPOOptimizer.update": { "total": 556.3841084330352, "count": 38580, "is_parallel": true, "self": 556.3841084330352 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1260215050001534, "count": 1, "self": 0.0008633620000182418, "children": { "RLTrainer._checkpoint": { "total": 0.12515814300013517, "count": 1, "self": 0.12515814300013517 } } } } } } }