{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0226633548736572, "min": 1.0226633548736572, "max": 2.86620831489563, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9798.1376953125, "min": 9798.1376953125, "max": 29447.423828125, "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": 12.580914497375488, "min": 0.34192419052124023, "max": 12.580914497375488, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2453.2783203125, "min": 66.33329010009766, "max": 2548.0009765625, "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": 0.0732054379862829, "min": 0.0633926324388834, "max": 0.0767856136794138, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2928217519451316, "min": 0.2535705297555336, "max": 0.3715693132490189, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21818503664404737, "min": 0.11929301922346519, "max": 0.2632536495433134, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8727401465761895, "min": 0.47717207689386076, "max": 1.3162682477165668, "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": 24.772727272727273, "min": 3.477272727272727, "max": 25.036363636363635, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1090.0, "min": 153.0, "max": 1377.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.772727272727273, "min": 3.477272727272727, "max": 25.036363636363635, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1090.0, "min": 153.0, "max": 1377.0, "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": "1702996002", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/dubik/anaconda3/envs/DRL/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --force", "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": "1702996189" }, "total": 186.6811085370009, "count": 1, "self": 0.21745397000086086, "children": { "run_training.setup": { "total": 0.014709783999933279, "count": 1, "self": 0.014709783999933279 }, "TrainerController.start_learning": { "total": 186.44894478300012, "count": 1, "self": 0.2720452509674942, "children": { "TrainerController._reset_env": { "total": 3.5815433799998573, "count": 1, "self": 3.5815433799998573 }, "TrainerController.advance": { "total": 182.54611101703267, "count": 18202, "self": 0.1356537320843927, "children": { "env_step": { "total": 182.41045728494828, "count": 18202, "self": 119.65857985082584, "children": { "SubprocessEnvManager._take_step": { "total": 62.620460314117736, "count": 18202, "self": 0.6310128262375656, "children": { "TorchPolicy.evaluate": { "total": 61.98944748788017, "count": 18202, "self": 61.98944748788017 } } }, "workers": { "total": 0.13141712000469852, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 186.13554249491062, "count": 18202, "is_parallel": true, "self": 102.17813146188928, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009561490005580708, "count": 1, "is_parallel": true, "self": 0.00025674599601188675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006994030045461841, "count": 10, "is_parallel": true, "self": 0.0006994030045461841 } } }, "UnityEnvironment.step": { "total": 0.013326149999556947, "count": 1, "is_parallel": true, "self": 0.00018745600027614273, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014573599946743343, "count": 1, "is_parallel": true, "self": 0.00014573599946743343 }, "communicator.exchange": { "total": 0.012381565000396222, "count": 1, "is_parallel": true, "self": 0.012381565000396222 }, "steps_from_proto": { "total": 0.0006113929994171485, "count": 1, "is_parallel": true, "self": 0.00013947500156064052, "children": { "_process_rank_one_or_two_observation": { "total": 0.000471917997856508, "count": 10, "is_parallel": true, "self": 0.000471917997856508 } } } } } } }, "UnityEnvironment.step": { "total": 83.95741103302134, "count": 18201, "is_parallel": true, "self": 3.517649104063821, "children": { "UnityEnvironment._generate_step_input": { "total": 2.0151639058713045, "count": 18201, "is_parallel": true, "self": 2.0151639058713045 }, "communicator.exchange": { "total": 67.12336918403889, "count": 18201, "is_parallel": true, "self": 67.12336918403889 }, "steps_from_proto": { "total": 11.301228839047326, "count": 18201, "is_parallel": true, "self": 2.406074425414772, "children": { "_process_rank_one_or_two_observation": { "total": 8.895154413632554, "count": 182010, "is_parallel": true, "self": 8.895154413632554 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.633500015595928e-05, "count": 1, "self": 6.633500015595928e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 182.43436464393562, "count": 133443, "is_parallel": true, "self": 0.8969640038085345, "children": { "process_trajectory": { "total": 101.38305206212863, "count": 133443, "is_parallel": true, "self": 101.09202700313108, "children": { "RLTrainer._checkpoint": { "total": 0.2910250589975476, "count": 4, "is_parallel": true, "self": 0.2910250589975476 } } }, "_update_policy": { "total": 80.15434857799846, "count": 90, "is_parallel": true, "self": 19.50633270304752, "children": { "TorchPPOOptimizer.update": { "total": 60.64801587495094, "count": 4587, "is_parallel": true, "self": 60.64801587495094 } } } } } } } } }, "TrainerController._save_models": { "total": 0.04917879999993602, "count": 1, "self": 0.0005315660000633216, "children": { "RLTrainer._checkpoint": { "total": 0.0486472339998727, "count": 1, "self": 0.0486472339998727 } } } } } } }