{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9797917604446411, "min": 0.9797917604446411, "max": 2.8613667488098145, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9441.2734375, "min": 9441.2734375, "max": 29271.78125, "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": 12.83474349975586, "min": 0.4273349642753601, "max": 12.83474349975586, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2502.77490234375, "min": 82.90298461914062, "max": 2616.813232421875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07090907499471487, "min": 0.06159887070646387, "max": 0.0737017140191336, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2836362999788595, "min": 0.24639548282585547, "max": 0.3547285573686881, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20557681105884854, "min": 0.10387760635428861, "max": 0.28857248020449694, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8223072442353941, "min": 0.41551042541715444, "max": 1.4428624010224846, "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": 25.15909090909091, "min": 3.25, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 143.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.25, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 143.0, "max": 1401.0, "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": "1703063802", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703064258" }, "total": 455.86336659599993, "count": 1, "self": 0.6357529939999722, "children": { "run_training.setup": { "total": 0.05162072699999953, "count": 1, "self": 0.05162072699999953 }, "TrainerController.start_learning": { "total": 455.17599287499996, "count": 1, "self": 0.6069434259961781, "children": { "TrainerController._reset_env": { "total": 2.9977768420000643, "count": 1, "self": 2.9977768420000643 }, "TrainerController.advance": { "total": 451.4383680690037, "count": 18217, "self": 0.28954673101736716, "children": { "env_step": { "total": 451.1488213379863, "count": 18217, "self": 296.7735287459965, "children": { "SubprocessEnvManager._take_step": { "total": 154.08172861099888, "count": 18217, "self": 1.492846075994521, "children": { "TorchPolicy.evaluate": { "total": 152.58888253500436, "count": 18217, "self": 152.58888253500436 } } }, "workers": { "total": 0.29356398099093894, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 453.858201473008, "count": 18217, "is_parallel": true, "self": 223.40021484701316, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004857184999991659, "count": 1, "is_parallel": true, "self": 0.003352654000025268, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015045309999663914, "count": 10, "is_parallel": true, "self": 0.0015045309999663914 } } }, "UnityEnvironment.step": { "total": 0.040608540999983234, "count": 1, "is_parallel": true, "self": 0.0006350459998429869, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041615100008129957, "count": 1, "is_parallel": true, "self": 0.00041615100008129957 }, "communicator.exchange": { "total": 0.0372944189999771, "count": 1, "is_parallel": true, "self": 0.0372944189999771 }, "steps_from_proto": { "total": 0.00226292500008185, "count": 1, "is_parallel": true, "self": 0.0005105620001586431, "children": { "_process_rank_one_or_two_observation": { "total": 0.001752362999923207, "count": 10, "is_parallel": true, "self": 0.001752362999923207 } } } } } } }, "UnityEnvironment.step": { "total": 230.45798662599486, "count": 18216, "is_parallel": true, "self": 10.653750300990964, "children": { "UnityEnvironment._generate_step_input": { "total": 5.63513402199726, "count": 18216, "is_parallel": true, "self": 5.63513402199726 }, "communicator.exchange": { "total": 179.470979419007, "count": 18216, "is_parallel": true, "self": 179.470979419007 }, "steps_from_proto": { "total": 34.698122883999645, "count": 18216, "is_parallel": true, "self": 6.4321613830010165, "children": { "_process_rank_one_or_two_observation": { "total": 28.26596150099863, "count": 182160, "is_parallel": true, "self": 28.26596150099863 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001300070000525011, "count": 1, "self": 0.0001300070000525011, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 445.65038788794686, "count": 687564, "is_parallel": true, "self": 14.56625286094959, "children": { "process_trajectory": { "total": 246.112817557997, "count": 687564, "is_parallel": true, "self": 245.174190430997, "children": { "RLTrainer._checkpoint": { "total": 0.9386271270000179, "count": 4, "is_parallel": true, "self": 0.9386271270000179 } } }, "_update_policy": { "total": 184.97131746900027, "count": 90, "is_parallel": true, "self": 56.618600249999076, "children": { "TorchPPOOptimizer.update": { "total": 128.3527172190012, "count": 4584, "is_parallel": true, "self": 128.3527172190012 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13277453099999548, "count": 1, "self": 0.0010213639999392399, "children": { "RLTrainer._checkpoint": { "total": 0.13175316700005624, "count": 1, "self": 0.13175316700005624 } } } } } } }