{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.040476679801941, "min": 1.040476679801941, "max": 2.8712003231048584, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9968.8076171875, "min": 9968.8076171875, "max": 29435.544921875, "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": 13.02307415008545, "min": 0.30633246898651123, "max": 13.02307415008545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2539.49951171875, "min": 59.42850112915039, "max": 2617.337890625, "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": 0.06668720387660512, "min": 0.06388316592087458, "max": 0.07466405285366837, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2667488155064205, "min": 0.2667488155064205, "max": 0.3662974968645037, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18654012044563012, "min": 0.12978840062700614, "max": 0.28281048881072623, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7461604817825205, "min": 0.5191536025080246, "max": 1.414052444053631, "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": 26.022727272727273, "min": 3.227272727272727, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1145.0, "min": 142.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.022727272727273, "min": 3.227272727272727, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1145.0, "min": 142.0, "max": 1428.0, "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": "1726327193", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --force --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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726327553" }, "total": 359.9692777569999, "count": 1, "self": 0.16821409400017728, "children": { "run_training.setup": { "total": 0.02799014799984434, "count": 1, "self": 0.02799014799984434 }, "TrainerController.start_learning": { "total": 359.77307351499985, "count": 1, "self": 0.3602390050264148, "children": { "TrainerController._reset_env": { "total": 1.3846198879996336, "count": 1, "self": 1.3846198879996336 }, "TrainerController.advance": { "total": 357.98075265197394, "count": 18203, "self": 0.19742544096561687, "children": { "env_step": { "total": 357.7833272110083, "count": 18203, "self": 199.7510763599712, "children": { "SubprocessEnvManager._take_step": { "total": 157.85180172004175, "count": 18203, "self": 0.9977100950336535, "children": { "TorchPolicy.evaluate": { "total": 156.8540916250081, "count": 18203, "self": 156.8540916250081 } } }, "workers": { "total": 0.18044913099538462, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 359.0971838200394, "count": 18203, "is_parallel": true, "self": 207.87618567699565, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010926619997917442, "count": 1, "is_parallel": true, "self": 0.00033093400043071597, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007617279993610282, "count": 10, "is_parallel": true, "self": 0.0007617279993610282 } } }, "UnityEnvironment.step": { "total": 0.016477728000154457, "count": 1, "is_parallel": true, "self": 0.00020291100054237177, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00013170900001568953, "count": 1, "is_parallel": true, "self": 0.00013170900001568953 }, "communicator.exchange": { "total": 0.015612361999956192, "count": 1, "is_parallel": true, "self": 0.015612361999956192 }, "steps_from_proto": { "total": 0.0005307459996402031, "count": 1, "is_parallel": true, "self": 0.00012311899899941636, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004076270006407867, "count": 10, "is_parallel": true, "self": 0.0004076270006407867 } } } } } } }, "UnityEnvironment.step": { "total": 151.22099814304374, "count": 18202, "is_parallel": true, "self": 3.628791283138071, "children": { "UnityEnvironment._generate_step_input": { "total": 2.008947236982749, "count": 18202, "is_parallel": true, "self": 2.008947236982749 }, "communicator.exchange": { "total": 136.18119026697013, "count": 18202, "is_parallel": true, "self": 136.18119026697013 }, "steps_from_proto": { "total": 9.40206935595279, "count": 18202, "is_parallel": true, "self": 2.1451517279360814, "children": { "_process_rank_one_or_two_observation": { "total": 7.2569176280167085, "count": 182020, "is_parallel": true, "self": 7.2569176280167085 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.405699969036505e-05, "count": 1, "self": 6.405699969036505e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 356.5667803719407, "count": 328572, "is_parallel": true, "self": 4.169351669860134, "children": { "process_trajectory": { "total": 202.27259958207605, "count": 328572, "is_parallel": true, "self": 201.88094826407678, "children": { "RLTrainer._checkpoint": { "total": 0.3916513179992762, "count": 4, "is_parallel": true, "self": 0.3916513179992762 } } }, "_update_policy": { "total": 150.1248291200045, "count": 90, "is_parallel": true, "self": 22.123458320997997, "children": { "TorchPPOOptimizer.update": { "total": 128.0013707990065, "count": 4587, "is_parallel": true, "self": 128.0013707990065 } } } } } } } } }, "TrainerController._save_models": { "total": 0.047397913000168046, "count": 1, "self": 0.0005226759994911845, "children": { "RLTrainer._checkpoint": { "total": 0.04687523700067686, "count": 1, "self": 0.04687523700067686 } } } } } } }