{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.017268419265747, "min": 1.017268419265747, "max": 2.8721466064453125, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9724.068359375, "min": 9724.068359375, "max": 29413.65234375, "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": 12.12628173828125, "min": 0.2181510180234909, "max": 12.12628173828125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2364.625, "min": 42.32129669189453, "max": 2452.10107421875, "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": 0.06839570581545487, "min": 0.06128784605557573, "max": 0.07520086727259588, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2735828232618195, "min": 0.25332135737984324, "max": 0.3549833118590779, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20261605087594659, "min": 0.13159241826232412, "max": 0.28442770604993783, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8104642035037863, "min": 0.5263696730492965, "max": 1.4221385302496892, "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": 24.227272727272727, "min": 3.5, "max": 24.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1066.0, "min": 154.0, "max": 1326.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.227272727272727, "min": 3.5, "max": 24.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1066.0, "min": 154.0, "max": 1326.0, "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": "1675868273", "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": "1675868737" }, "total": 463.8420540479999, "count": 1, "self": 0.6873125550000623, "children": { "run_training.setup": { "total": 0.11041602000000239, "count": 1, "self": 0.11041602000000239 }, "TrainerController.start_learning": { "total": 463.04432547299984, "count": 1, "self": 0.5421106910019944, "children": { "TrainerController._reset_env": { "total": 8.902112783999996, "count": 1, "self": 8.902112783999996 }, "TrainerController.advance": { "total": 453.4118823669978, "count": 18203, "self": 0.2915912739980513, "children": { "env_step": { "total": 453.12029109299976, "count": 18203, "self": 314.29906358201424, "children": { "SubprocessEnvManager._take_step": { "total": 138.53578375498728, "count": 18203, "self": 1.4664843079856382, "children": { "TorchPolicy.evaluate": { "total": 137.06929944700164, "count": 18203, "self": 30.253128973001594, "children": { "TorchPolicy.sample_actions": { "total": 106.81617047400005, "count": 18203, "self": 106.81617047400005 } } } } }, "workers": { "total": 0.28544375599824434, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 461.3286575160038, "count": 18203, "is_parallel": true, "self": 219.45410081200623, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0057820409999749245, "count": 1, "is_parallel": true, "self": 0.003669236999826353, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021128040001485715, "count": 10, "is_parallel": true, "self": 0.0021128040001485715 } } }, "UnityEnvironment.step": { "total": 0.0937779909999108, "count": 1, "is_parallel": true, "self": 0.0005945349998910388, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041820999990704877, "count": 1, "is_parallel": true, "self": 0.00041820999990704877 }, "communicator.exchange": { "total": 0.09090170500007844, "count": 1, "is_parallel": true, "self": 0.09090170500007844 }, "steps_from_proto": { "total": 0.0018635410000342745, "count": 1, "is_parallel": true, "self": 0.0005253220000440706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013382189999902039, "count": 10, "is_parallel": true, "self": 0.0013382189999902039 } } } } } } }, "UnityEnvironment.step": { "total": 241.87455670399754, "count": 18202, "is_parallel": true, "self": 9.48140543099123, "children": { "UnityEnvironment._generate_step_input": { "total": 5.283467728007395, "count": 18202, "is_parallel": true, "self": 5.283467728007395 }, "communicator.exchange": { "total": 195.8674799729987, "count": 18202, "is_parallel": true, "self": 195.8674799729987 }, "steps_from_proto": { "total": 31.24220357200022, "count": 18202, "is_parallel": true, "self": 7.077597823022188, "children": { "_process_rank_one_or_two_observation": { "total": 24.164605748978033, "count": 182020, "is_parallel": true, "self": 24.164605748978033 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012941699992552458, "count": 1, "self": 0.00012941699992552458, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 450.1485713850043, "count": 413756, "is_parallel": true, "self": 9.994485292024251, "children": { "process_trajectory": { "total": 258.17627051998045, "count": 413756, "is_parallel": true, "self": 257.2973164179806, "children": { "RLTrainer._checkpoint": { "total": 0.8789541019998524, "count": 4, "is_parallel": true, "self": 0.8789541019998524 } } }, "_update_policy": { "total": 181.9778155729996, "count": 90, "is_parallel": true, "self": 63.254127121004444, "children": { "TorchPPOOptimizer.update": { "total": 118.72368845199514, "count": 4587, "is_parallel": true, "self": 118.72368845199514 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1880902140001126, "count": 1, "self": 0.0010930420000931917, "children": { "RLTrainer._checkpoint": { "total": 0.18699717200001942, "count": 1, "self": 0.18699717200001942 } } } } } } }