{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7915663719177246, "min": 0.7915663719177246, "max": 2.8605520725250244, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7575.2900390625, "min": 7575.2900390625, "max": 29294.9140625, "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": 12.195801734924316, "min": 0.35566091537475586, "max": 12.195801734924316, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2378.181396484375, "min": 68.99821472167969, "max": 2444.375244140625, "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": 0.07220219119378325, "min": 0.06345995346468865, "max": 0.07727561690733316, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.288808764775133, "min": 0.259635906483905, "max": 0.36994490205018105, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.196659278781975, "min": 0.1350600476497693, "max": 0.2996963949910566, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7866371151279, "min": 0.5402401905990772, "max": 1.3595155331433988, "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": 24.363636363636363, "min": 4.0, "max": 24.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1072.0, "min": 176.0, "max": 1323.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.363636363636363, "min": 4.0, "max": 24.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1072.0, "min": 176.0, "max": 1323.0, "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": "1727188229", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727188832" }, "total": 603.40808571, "count": 1, "self": 0.5288610129998688, "children": { "run_training.setup": { "total": 0.06646332899998697, "count": 1, "self": 0.06646332899998697 }, "TrainerController.start_learning": { "total": 602.8127613680001, "count": 1, "self": 0.8501456469844015, "children": { "TrainerController._reset_env": { "total": 2.929527498000027, "count": 1, "self": 2.929527498000027 }, "TrainerController.advance": { "total": 598.9458616520157, "count": 18203, "self": 0.42805665302137186, "children": { "env_step": { "total": 598.5178049989943, "count": 18203, "self": 461.6762550709878, "children": { "SubprocessEnvManager._take_step": { "total": 136.42176662599934, "count": 18203, "self": 2.497207145996697, "children": { "TorchPolicy.evaluate": { "total": 133.92455948000264, "count": 18203, "self": 133.92455948000264 } } }, "workers": { "total": 0.4197833020071471, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 600.8851192829989, "count": 18203, "is_parallel": true, "self": 283.25641566899696, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030737349999867547, "count": 1, "is_parallel": true, "self": 0.001231878999988112, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018418559999986428, "count": 10, "is_parallel": true, "self": 0.0018418559999986428 } } }, "UnityEnvironment.step": { "total": 0.04514517100000148, "count": 1, "is_parallel": true, "self": 0.0010262729999794828, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004780940000159717, "count": 1, "is_parallel": true, "self": 0.0004780940000159717 }, "communicator.exchange": { "total": 0.04041591300000391, "count": 1, "is_parallel": true, "self": 0.04041591300000391 }, "steps_from_proto": { "total": 0.003224891000002117, "count": 1, "is_parallel": true, "self": 0.0005658560000370016, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026590349999651153, "count": 10, "is_parallel": true, "self": 0.0026590349999651153 } } } } } } }, "UnityEnvironment.step": { "total": 317.6287036140019, "count": 18202, "is_parallel": true, "self": 15.120493946008082, "children": { "UnityEnvironment._generate_step_input": { "total": 7.536993255991206, "count": 18202, "is_parallel": true, "self": 7.536993255991206 }, "communicator.exchange": { "total": 250.4975586069989, "count": 18202, "is_parallel": true, "self": 250.4975586069989 }, "steps_from_proto": { "total": 44.47365780500371, "count": 18202, "is_parallel": true, "self": 8.706472404995566, "children": { "_process_rank_one_or_two_observation": { "total": 35.767185400008145, "count": 182020, "is_parallel": true, "self": 35.767185400008145 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001582840000082797, "count": 1, "self": 0.0001582840000082797, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 592.042574665954, "count": 783773, "is_parallel": true, "self": 17.74901656696568, "children": { "process_trajectory": { "total": 317.76282005198823, "count": 783773, "is_parallel": true, "self": 316.82572455398815, "children": { "RLTrainer._checkpoint": { "total": 0.9370954980000761, "count": 4, "is_parallel": true, "self": 0.9370954980000761 } } }, "_update_policy": { "total": 256.5307380470001, "count": 90, "is_parallel": true, "self": 72.07429869500373, "children": { "TorchPPOOptimizer.update": { "total": 184.45643935199638, "count": 4587, "is_parallel": true, "self": 184.45643935199638 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0870682869999655, "count": 1, "self": 0.0015237159999514915, "children": { "RLTrainer._checkpoint": { "total": 0.085544571000014, "count": 1, "self": 0.085544571000014 } } } } } } }