{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0097259283065796, "min": 1.0097259283065796, "max": 2.8643553256988525, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9629.755859375, "min": 9629.755859375, "max": 29333.86328125, "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": 12.865677833557129, "min": 0.47359827160835266, "max": 12.865677833557129, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2508.80712890625, "min": 91.87806701660156, "max": 2596.03515625, "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": 0.06638904183466152, "min": 0.06323320144278399, "max": 0.07221606689164023, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26555616733864607, "min": 0.25293280577113597, "max": 0.3582824703680315, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1972320733920616, "min": 0.14838477862227306, "max": 0.2924631295250911, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7889282935682465, "min": 0.5935391144890922, "max": 1.4623156476254557, "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": 25.454545454545453, "min": 4.295454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 189.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 4.295454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 189.0, "max": 1388.0, "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": "1690548444", "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": "1690548954" }, "total": 510.1291300099999, "count": 1, "self": 0.4880645329999993, "children": { "run_training.setup": { "total": 0.03582144699998935, "count": 1, "self": 0.03582144699998935 }, "TrainerController.start_learning": { "total": 509.60524402999994, "count": 1, "self": 0.6040673379951045, "children": { "TrainerController._reset_env": { "total": 5.004346912000017, "count": 1, "self": 5.004346912000017 }, "TrainerController.advance": { "total": 503.8287761800048, "count": 18200, "self": 0.3046742840069214, "children": { "env_step": { "total": 503.5241018959979, "count": 18200, "self": 365.9401100689921, "children": { "SubprocessEnvManager._take_step": { "total": 137.26688251901032, "count": 18200, "self": 1.9398206680000385, "children": { "TorchPolicy.evaluate": { "total": 135.32706185101028, "count": 18200, "self": 135.32706185101028 } } }, "workers": { "total": 0.3171093079954517, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 507.8232540739875, "count": 18200, "is_parallel": true, "self": 239.57696444197688, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005562991999966016, "count": 1, "is_parallel": true, "self": 0.004060883000022386, "children": { "_process_rank_one_or_two_observation": { "total": 0.00150210899994363, "count": 10, "is_parallel": true, "self": 0.00150210899994363 } } }, "UnityEnvironment.step": { "total": 0.04634669700004679, "count": 1, "is_parallel": true, "self": 0.0004860770000618686, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035090000000082, "count": 1, "is_parallel": true, "self": 0.00035090000000082 }, "communicator.exchange": { "total": 0.04292111799998111, "count": 1, "is_parallel": true, "self": 0.04292111799998111 }, "steps_from_proto": { "total": 0.002588602000002993, "count": 1, "is_parallel": true, "self": 0.0007971859999429398, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017914160000600532, "count": 10, "is_parallel": true, "self": 0.0017914160000600532 } } } } } } }, "UnityEnvironment.step": { "total": 268.24628963201064, "count": 18199, "is_parallel": true, "self": 11.418885362022422, "children": { "UnityEnvironment._generate_step_input": { "total": 5.9199014690038325, "count": 18199, "is_parallel": true, "self": 5.9199014690038325 }, "communicator.exchange": { "total": 211.6712915569894, "count": 18199, "is_parallel": true, "self": 211.6712915569894 }, "steps_from_proto": { "total": 39.236211243995, "count": 18199, "is_parallel": true, "self": 7.352025330993513, "children": { "_process_rank_one_or_two_observation": { "total": 31.884185913001488, "count": 181990, "is_parallel": true, "self": 31.884185913001488 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020986200001971156, "count": 1, "self": 0.00020986200001971156, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 499.6116593200311, "count": 474690, "is_parallel": true, "self": 11.688660707052861, "children": { "process_trajectory": { "total": 274.56949423797823, "count": 474690, "is_parallel": true, "self": 273.63449294097825, "children": { "RLTrainer._checkpoint": { "total": 0.9350012969999852, "count": 4, "is_parallel": true, "self": 0.9350012969999852 } } }, "_update_policy": { "total": 213.353504375, "count": 90, "is_parallel": true, "self": 82.52770948799986, "children": { "TorchPPOOptimizer.update": { "total": 130.82579488700014, "count": 4587, "is_parallel": true, "self": 130.82579488700014 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16784373799998775, "count": 1, "self": 0.0009557839999843054, "children": { "RLTrainer._checkpoint": { "total": 0.16688795400000345, "count": 1, "self": 0.16688795400000345 } } } } } } }