{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.84099942445755, "min": 0.84099942445755, "max": 2.8697006702423096, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8048.3642578125, "min": 8048.3642578125, "max": 29451.73828125, "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": 12.819323539733887, "min": 0.30684253573417664, "max": 12.819323539733887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.76806640625, "min": 59.52745056152344, "max": 2592.494873046875, "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": 0.06692133571603193, "min": 0.06177563469861756, "max": 0.07365187178020634, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2676853428641277, "min": 0.24710253879447025, "max": 0.36500927746893985, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20537949470328348, "min": 0.09216363705562282, "max": 0.2643341215802174, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8215179788131339, "min": 0.3686545482224913, "max": 1.3216706079010871, "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": 2.75, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 121.0, "max": 1385.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 2.75, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 121.0, "max": 1385.0, "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": "1679287468", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "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": "1679287936" }, "total": 468.042031813, "count": 1, "self": 0.4302461139998286, "children": { "run_training.setup": { "total": 0.10232763700003034, "count": 1, "self": 0.10232763700003034 }, "TrainerController.start_learning": { "total": 467.50945806200014, "count": 1, "self": 0.5136322209995114, "children": { "TrainerController._reset_env": { "total": 9.301476305000051, "count": 1, "self": 9.301476305000051 }, "TrainerController.advance": { "total": 457.5621709900008, "count": 18204, "self": 0.2622146870139659, "children": { "env_step": { "total": 457.29995630298686, "count": 18204, "self": 329.4158926009734, "children": { "SubprocessEnvManager._take_step": { "total": 127.62186527599135, "count": 18204, "self": 2.212752491985725, "children": { "TorchPolicy.evaluate": { "total": 125.40911278400563, "count": 18204, "self": 125.40911278400563 } } }, "workers": { "total": 0.26219842602210974, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 466.08130520600287, "count": 18204, "is_parallel": true, "self": 224.41827065599648, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005844182000032561, "count": 1, "is_parallel": true, "self": 0.004375514000003022, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014686680000295382, "count": 10, "is_parallel": true, "self": 0.0014686680000295382 } } }, "UnityEnvironment.step": { "total": 0.10426534400005494, "count": 1, "is_parallel": true, "self": 0.000578623000137668, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041031800003565877, "count": 1, "is_parallel": true, "self": 0.00041031800003565877 }, "communicator.exchange": { "total": 0.09832509699992897, "count": 1, "is_parallel": true, "self": 0.09832509699992897 }, "steps_from_proto": { "total": 0.004951305999952638, "count": 1, "is_parallel": true, "self": 0.0019768619997648784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029744440001877592, "count": 10, "is_parallel": true, "self": 0.0029744440001877592 } } } } } } }, "UnityEnvironment.step": { "total": 241.6630345500064, "count": 18203, "is_parallel": true, "self": 9.388898416996994, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2940915740017545, "count": 18203, "is_parallel": true, "self": 5.2940915740017545 }, "communicator.exchange": { "total": 195.4837719090126, "count": 18203, "is_parallel": true, "self": 195.4837719090126 }, "steps_from_proto": { "total": 31.496272649995035, "count": 18203, "is_parallel": true, "self": 6.236019759977694, "children": { "_process_rank_one_or_two_observation": { "total": 25.26025289001734, "count": 182030, "is_parallel": true, "self": 25.26025289001734 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011301799986540573, "count": 1, "self": 0.00011301799986540573, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 453.973135810029, "count": 413925, "is_parallel": true, "self": 10.220198568976116, "children": { "process_trajectory": { "total": 252.7678580040532, "count": 413925, "is_parallel": true, "self": 251.89290529005348, "children": { "RLTrainer._checkpoint": { "total": 0.8749527139997326, "count": 4, "is_parallel": true, "self": 0.8749527139997326 } } }, "_update_policy": { "total": 190.9850792369997, "count": 90, "is_parallel": true, "self": 69.59313257600206, "children": { "TorchPPOOptimizer.update": { "total": 121.39194666099763, "count": 4587, "is_parallel": true, "self": 121.39194666099763 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13206552799988458, "count": 1, "self": 0.0010672229998363036, "children": { "RLTrainer._checkpoint": { "total": 0.13099830500004828, "count": 1, "self": 0.13099830500004828 } } } } } } }