{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1063027381896973, "min": 1.0979952812194824, "max": 2.871321439743042, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10562.978515625, "min": 10562.978515625, "max": 29499.95703125, "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": 12.447012901306152, "min": 0.4224646985530853, "max": 12.447012901306152, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2427.16748046875, "min": 81.9581527709961, "max": 2496.465087890625, "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": 0.0680802553817878, "min": 0.06014252547291678, "max": 0.07632606763831527, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2723210215271512, "min": 0.2503388118462217, "max": 0.35971706249185054, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2085458694354576, "min": 0.1165344900047571, "max": 0.27813386223187636, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8341834777418304, "min": 0.4661379600190284, "max": 1.3857629413113877, "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": 24.954545454545453, "min": 3.772727272727273, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 166.0, "max": 1330.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.772727272727273, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 166.0, "max": 1330.0, "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": "1690473569", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.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": "1690474067" }, "total": 497.945676546, "count": 1, "self": 0.835398519000023, "children": { "run_training.setup": { "total": 0.0556766830000015, "count": 1, "self": 0.0556766830000015 }, "TrainerController.start_learning": { "total": 497.054601344, "count": 1, "self": 0.5769783049886428, "children": { "TrainerController._reset_env": { "total": 5.8502916709999795, "count": 1, "self": 5.8502916709999795 }, "TrainerController.advance": { "total": 490.38094480701136, "count": 18219, "self": 0.2856185400062259, "children": { "env_step": { "total": 490.09532626700513, "count": 18219, "self": 355.31409618100474, "children": { "SubprocessEnvManager._take_step": { "total": 134.4851476739949, "count": 18219, "self": 1.9607658549967368, "children": { "TorchPolicy.evaluate": { "total": 132.52438181899817, "count": 18219, "self": 132.52438181899817 } } }, "workers": { "total": 0.29608241200548946, "count": 18219, "self": 0.0, "children": { "worker_root": { "total": 495.3952223919936, "count": 18219, "is_parallel": true, "self": 235.66279135298976, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0054974759999595335, "count": 1, "is_parallel": true, "self": 0.003976731999898675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015207440000608585, "count": 10, "is_parallel": true, "self": 0.0015207440000608585 } } }, "UnityEnvironment.step": { "total": 0.0373264899999981, "count": 1, "is_parallel": true, "self": 0.0007138590000295153, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034540199999355536, "count": 1, "is_parallel": true, "self": 0.00034540199999355536 }, "communicator.exchange": { "total": 0.03385186299999532, "count": 1, "is_parallel": true, "self": 0.03385186299999532 }, "steps_from_proto": { "total": 0.002415365999979713, "count": 1, "is_parallel": true, "self": 0.0004329140000436382, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019824519999360746, "count": 10, "is_parallel": true, "self": 0.0019824519999360746 } } } } } } }, "UnityEnvironment.step": { "total": 259.73243103900387, "count": 18218, "is_parallel": true, "self": 11.222122656995907, "children": { "UnityEnvironment._generate_step_input": { "total": 5.464670690003572, "count": 18218, "is_parallel": true, "self": 5.464670690003572 }, "communicator.exchange": { "total": 205.80449946900194, "count": 18218, "is_parallel": true, "self": 205.80449946900194 }, "steps_from_proto": { "total": 37.24113822300245, "count": 18218, "is_parallel": true, "self": 6.833339087970387, "children": { "_process_rank_one_or_two_observation": { "total": 30.407799135032064, "count": 182180, "is_parallel": true, "self": 30.407799135032064 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011804100006429508, "count": 1, "self": 0.00011804100006429508, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 486.3396166559678, "count": 455920, "is_parallel": true, "self": 10.784608052924625, "children": { "process_trajectory": { "total": 265.83560848004277, "count": 455920, "is_parallel": true, "self": 264.55699971204285, "children": { "RLTrainer._checkpoint": { "total": 1.2786087679999127, "count": 4, "is_parallel": true, "self": 1.2786087679999127 } } }, "_update_policy": { "total": 209.7194001230004, "count": 90, "is_parallel": true, "self": 83.03952556699795, "children": { "TorchPPOOptimizer.update": { "total": 126.67987455600246, "count": 4587, "is_parallel": true, "self": 126.67987455600246 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24626851999994415, "count": 1, "self": 0.0014649199998757467, "children": { "RLTrainer._checkpoint": { "total": 0.2448036000000684, "count": 1, "self": 0.2448036000000684 } } } } } } }