{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8744990825653076, "min": 0.8744990825653076, "max": 2.689220905303955, "count": 19 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8311.2392578125, "min": 8311.2392578125, "max": 24037.5703125, "count": 19 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 19 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.070773124694824, "min": 1.8401113748550415, "max": 13.152746200561523, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2548.80078125, "min": 248.4150390625, "max": 2683.16015625, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06752626162686319, "min": 0.06362210695692293, "max": 0.07188466612270156, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27010504650745276, "min": 0.1961168509897463, "max": 0.3587258256168342, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24088581169352813, "min": 0.18131211524208385, "max": 0.2990148761400989, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9635432467741125, "min": 0.7252484609683354, "max": 1.31407735043881, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000273732008756, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00123666008778, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.191244, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.91222, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0045630756, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.020619778000000002, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 6567.0, "max": 10945.0, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.386363636363637, "min": 8.545454545454545, "max": 25.98181818181818, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 282.0, "max": 1429.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 8.545454545454545, "max": 25.98181818181818, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 282.0, "max": 1429.0, "count": 19 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1793185363", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "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": "1793185763" }, "total": 399.9505475400001, "count": 1, "self": 0.4293778139990536, "children": { "run_training.setup": { "total": 0.026504938000471157, "count": 1, "self": 0.026504938000471157 }, "TrainerController.start_learning": { "total": 399.4946647880006, "count": 1, "self": 0.3596905190161124, "children": { "TrainerController._reset_env": { "total": 2.029048638999484, "count": 1, "self": 2.029048638999484 }, "TrainerController.advance": { "total": 396.99879928998416, "count": 16992, "self": 0.3697570749754959, "children": { "env_step": { "total": 291.3942676600609, "count": 16992, "self": 224.72231780010134, "children": { "SubprocessEnvManager._take_step": { "total": 66.44963594695946, "count": 16992, "self": 1.207205362017703, "children": { "TorchPolicy.evaluate": { "total": 65.24243058494176, "count": 16992, "self": 65.24243058494176 } } }, "workers": { "total": 0.22231391300010728, "count": 16992, "self": 0.0, "children": { "worker_root": { "total": 398.3097697439953, "count": 16992, "is_parallel": true, "self": 200.86815691394077, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019634359996416606, "count": 1, "is_parallel": true, "self": 0.0006310820008366136, "children": { "_process_rank_one_or_two_observation": { "total": 0.001332353998805047, "count": 10, "is_parallel": true, "self": 0.001332353998805047 } } }, "UnityEnvironment.step": { "total": 0.03765169899998, "count": 1, "is_parallel": true, "self": 0.0005635990000882884, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043332899986125994, "count": 1, "is_parallel": true, "self": 0.00043332899986125994 }, "communicator.exchange": { "total": 0.03280234700014262, "count": 1, "is_parallel": true, "self": 0.03280234700014262 }, "steps_from_proto": { "total": 0.003852423999887833, "count": 1, "is_parallel": true, "self": 0.0006220149980435963, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032304090018442366, "count": 10, "is_parallel": true, "self": 0.0032304090018442366 } } } } } } }, "UnityEnvironment.step": { "total": 197.4416128300545, "count": 16991, "is_parallel": true, "self": 9.757482763118787, "children": { "UnityEnvironment._generate_step_input": { "total": 5.271026883026934, "count": 16991, "is_parallel": true, "self": 5.271026883026934 }, "communicator.exchange": { "total": 150.0277315199728, "count": 16991, "is_parallel": true, "self": 150.0277315199728 }, "steps_from_proto": { "total": 32.385371663935985, "count": 16991, "is_parallel": true, "self": 5.762692382989371, "children": { "_process_rank_one_or_two_observation": { "total": 26.622679280946613, "count": 169910, "is_parallel": true, "self": 26.622679280946613 } } } } } } } } } } }, "trainer_advance": { "total": 105.23477455494776, "count": 16992, "self": 0.4517547629711771, "children": { "process_trajectory": { "total": 21.944141636974564, "count": 16992, "self": 21.531232170974363, "children": { "RLTrainer._checkpoint": { "total": 0.41290946600020106, "count": 4, "self": 0.41290946600020106 } } }, "_update_policy": { "total": 82.83887815500202, "count": 84, "self": 33.000386305989196, "children": { "TorchPPOOptimizer.update": { "total": 49.838491849012826, "count": 4281, "self": 49.838491849012826 } } } } } } }, "trainer_threads": { "total": 9.430004865862429e-07, "count": 1, "self": 9.430004865862429e-07 }, "TrainerController._save_models": { "total": 0.1071253970003454, "count": 1, "self": 0.0012766930003635935, "children": { "RLTrainer._checkpoint": { "total": 0.10584870399998181, "count": 1, "self": 0.10584870399998181 } } } } } } }