{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.767365574836731, "min": 0.767365574836731, "max": 2.850863456726074, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7293.04248046875, "min": 7293.04248046875, "max": 29101.61328125, "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": 11.886533737182617, "min": 0.35460880398750305, "max": 11.886533737182617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2317.8740234375, "min": 68.79410552978516, "max": 2400.44189453125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06998586334635085, "min": 0.06494176728915145, "max": 0.07326285483349256, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2799434533854034, "min": 0.2597670691566058, "max": 0.36268193953939915, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1795884622808765, "min": 0.12012172712232261, "max": 0.30633903268505547, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.718353849123506, "min": 0.48048690848929043, "max": 1.5316951634252773, "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.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.Environment.CumulativeReward.mean": { "value": 23.363636363636363, "min": 3.409090909090909, "max": 23.581818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1028.0, "min": 150.0, "max": 1297.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.363636363636363, "min": 3.409090909090909, "max": 23.581818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1028.0, "min": 150.0, "max": 1297.0, "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": "1758768852", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1758769321" }, "total": 468.636550326, "count": 1, "self": 0.42587020600001324, "children": { "run_training.setup": { "total": 0.024310323999998218, "count": 1, "self": 0.024310323999998218 }, "TrainerController.start_learning": { "total": 468.186369796, "count": 1, "self": 0.4516250589858828, "children": { "TrainerController._reset_env": { "total": 3.316366437999932, "count": 1, "self": 3.316366437999932 }, "TrainerController.advance": { "total": 464.3267597450142, "count": 18192, "self": 0.4576330150131298, "children": { "env_step": { "total": 343.77086070902567, "count": 18192, "self": 268.5574222530131, "children": { "SubprocessEnvManager._take_step": { "total": 74.93267605200083, "count": 18192, "self": 1.3735364589857681, "children": { "TorchPolicy.evaluate": { "total": 73.55913959301506, "count": 18192, "self": 73.55913959301506 } } }, "workers": { "total": 0.2807624040117389, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 466.2195555709918, "count": 18192, "is_parallel": true, "self": 231.3699763490049, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006991564000031758, "count": 1, "is_parallel": true, "self": 0.004829657999948722, "children": { "_process_rank_one_or_two_observation": { "total": 0.002161906000083036, "count": 10, "is_parallel": true, "self": 0.002161906000083036 } } }, "UnityEnvironment.step": { "total": 0.0360362520000308, "count": 1, "is_parallel": true, "self": 0.0005788710001297659, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004069569999956002, "count": 1, "is_parallel": true, "self": 0.0004069569999956002 }, "communicator.exchange": { "total": 0.03311069899996255, "count": 1, "is_parallel": true, "self": 0.03311069899996255 }, "steps_from_proto": { "total": 0.0019397249999428823, "count": 1, "is_parallel": true, "self": 0.00035062599977209175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015890990001707905, "count": 10, "is_parallel": true, "self": 0.0015890990001707905 } } } } } } }, "UnityEnvironment.step": { "total": 234.84957922198691, "count": 18191, "is_parallel": true, "self": 10.526341537985104, "children": { "UnityEnvironment._generate_step_input": { "total": 5.601786737994303, "count": 18191, "is_parallel": true, "self": 5.601786737994303 }, "communicator.exchange": { "total": 180.22431779900126, "count": 18191, "is_parallel": true, "self": 180.22431779900126 }, "steps_from_proto": { "total": 38.49713314700625, "count": 18191, "is_parallel": true, "self": 7.116228671053136, "children": { "_process_rank_one_or_two_observation": { "total": 31.380904475953116, "count": 181910, "is_parallel": true, "self": 31.380904475953116 } } } } } } } } } } }, "trainer_advance": { "total": 120.09826602097542, "count": 18192, "self": 0.5669130869748642, "children": { "process_trajectory": { "total": 27.043860608000955, "count": 18192, "self": 26.53747564600087, "children": { "RLTrainer._checkpoint": { "total": 0.5063849620000838, "count": 5, "self": 0.5063849620000838 } } }, "_update_policy": { "total": 92.4874923259996, "count": 90, "self": 37.06882153499839, "children": { "TorchPPOOptimizer.update": { "total": 55.418670791001205, "count": 4587, "self": 55.418670791001205 } } } } } } }, "trainer_threads": { "total": 1.2040000001434237e-06, "count": 1, "self": 1.2040000001434237e-06 }, "TrainerController._save_models": { "total": 0.09161734999997861, "count": 1, "self": 0.0008787289998508641, "children": { "RLTrainer._checkpoint": { "total": 0.09073862100012775, "count": 1, "self": 0.09073862100012775 } } } } } } }