{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0387177467346191, "min": 1.029460072517395, "max": 2.8555908203125, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9951.955078125, "min": 9951.955078125, "max": 29306.927734375, "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": 11.479519844055176, "min": 0.5112997889518738, "max": 11.479519844055176, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2238.50634765625, "min": 99.19215393066406, "max": 2305.64697265625, "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": 0.06547126209297144, "min": 0.057847231564700646, "max": 0.07298672518435542, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26188504837188575, "min": 0.23138892625880259, "max": 0.3577886864117246, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19844445615422493, "min": 0.11652297785907399, "max": 0.26031874353979145, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7937778246168997, "min": 0.46609191143629597, "max": 1.213502541476605, "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": 23.022727272727273, "min": 3.5454545454545454, "max": 23.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1013.0, "min": 156.0, "max": 1249.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.022727272727273, "min": 3.5454545454545454, "max": 23.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1013.0, "min": 156.0, "max": 1249.0, "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": "1674306823", "python_version": "3.8.15 (default, Nov 24 2022, 15:19:38) \n[GCC 11.2.0]", "command_line_arguments": "/home/boris.ustyugov/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.2", "numpy_version": "1.23.4", "end_time_seconds": "1674307221" }, "total": 397.76997532788664, "count": 1, "self": 0.2706591780297458, "children": { "run_training.setup": { "total": 0.0184606839902699, "count": 1, "self": 0.0184606839902699 }, "TrainerController.start_learning": { "total": 397.4808554658666, "count": 1, "self": 0.3135979864746332, "children": { "TrainerController._reset_env": { "total": 4.812337328214198, "count": 1, "self": 4.812337328214198 }, "TrainerController.advance": { "total": 392.2721786182374, "count": 18206, "self": 0.14350059814751148, "children": { "env_step": { "total": 392.12867802008986, "count": 18206, "self": 318.25488693173975, "children": { "SubprocessEnvManager._take_step": { "total": 73.72526533342898, "count": 18206, "self": 0.8523282194510102, "children": { "TorchPolicy.evaluate": { "total": 72.87293711397797, "count": 18206, "self": 14.314334282651544, "children": { "TorchPolicy.sample_actions": { "total": 58.558602831326425, "count": 18206, "self": 58.558602831326425 } } } } }, "workers": { "total": 0.1485257549211383, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 396.4749723067507, "count": 18206, "is_parallel": true, "self": 134.92124743154272, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003544424194842577, "count": 1, "is_parallel": true, "self": 0.000977831892669201, "children": { "_process_rank_one_or_two_observation": { "total": 0.002566592302173376, "count": 10, "is_parallel": true, "self": 0.002566592302173376 } } }, "UnityEnvironment.step": { "total": 0.034516389947384596, "count": 1, "is_parallel": true, "self": 0.0007411674596369267, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005438909865915775, "count": 1, "is_parallel": true, "self": 0.0005438909865915775 }, "communicator.exchange": { "total": 0.030873256269842386, "count": 1, "is_parallel": true, "self": 0.030873256269842386 }, "steps_from_proto": { "total": 0.0023580752313137054, "count": 1, "is_parallel": true, "self": 0.0005376893095672131, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018203859217464924, "count": 10, "is_parallel": true, "self": 0.0018203859217464924 } } } } } } }, "UnityEnvironment.step": { "total": 261.553724875208, "count": 18205, "is_parallel": true, "self": 12.686800167895854, "children": { "UnityEnvironment._generate_step_input": { "total": 6.717377104796469, "count": 18205, "is_parallel": true, "self": 6.717377104796469 }, "communicator.exchange": { "total": 203.50497713824734, "count": 18205, "is_parallel": true, "self": 203.50497713824734 }, "steps_from_proto": { "total": 38.64457046426833, "count": 18205, "is_parallel": true, "self": 7.8639676556922495, "children": { "_process_rank_one_or_two_observation": { "total": 30.780602808576077, "count": 182050, "is_parallel": true, "self": 30.780602808576077 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001025036908686161, "count": 1, "self": 0.0001025036908686161, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 391.4766505486332, "count": 206001, "is_parallel": true, "self": 2.6979417675174773, "children": { "process_trajectory": { "total": 236.16894423495978, "count": 206001, "is_parallel": true, "self": 235.3899759319611, "children": { "RLTrainer._checkpoint": { "total": 0.7789683029986918, "count": 4, "is_parallel": true, "self": 0.7789683029986918 } } }, "_update_policy": { "total": 152.60976454615593, "count": 90, "is_parallel": true, "self": 22.606808377429843, "children": { "TorchPPOOptimizer.update": { "total": 130.0029561687261, "count": 4587, "is_parallel": true, "self": 130.0029561687261 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08263902924954891, "count": 1, "self": 0.0005042273551225662, "children": { "RLTrainer._checkpoint": { "total": 0.08213480189442635, "count": 1, "self": 0.08213480189442635 } } } } } } }