{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2230117321014404, "min": 1.2230117321014404, "max": 2.8615801334381104, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10843.2216796875, "min": 10843.2216796875, "max": 31634.767578125, "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.Step.mean": { "value": 199800.0, "min": 9800.0, "max": 199800.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199800.0, "min": 9800.0, "max": 199800.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 2.6578848361968994, "min": 0.1388860046863556, "max": 2.6578848361968994, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 132.8942413330078, "min": 6.805414199829102, "max": 132.8942413330078, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.06, "min": 3.306122448979592, "max": 26.06, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1303.0, "min": 162.0, "max": 1303.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.06, "min": 3.306122448979592, "max": 26.06, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1303.0, "min": 162.0, "max": 1303.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06663666524086603, "min": 0.062078236376857034, "max": 0.07542671996177923, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26654666096346413, "min": 0.24831294550742813, "max": 0.3654332542928922, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1303019299007514, "min": 0.1107853918098936, "max": 0.16196015699237, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5212077196030056, "min": 0.45419704154425977, "max": 0.80980078496185, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00013250009735000013, "min": 0.00013250009735000013, "max": 0.0048625000027499995, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0005300003894000005, "min": 0.0005300003894000005, "max": 0.0230750000385, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10265, "min": 0.10265, "max": 0.19725000000000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4106, "min": 0.4106, "max": 0.9615, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014223500000000013, "min": 0.00014223500000000013, "max": 0.004862775, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005689400000000005, "min": 0.0005689400000000005, "max": 0.023078849999999998, "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": "1695401510", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1695401999" }, "total": 489.3164900869997, "count": 1, "self": 0.4249920430011116, "children": { "run_training.setup": { "total": 0.0627173489992856, "count": 1, "self": 0.0627173489992856 }, "TrainerController.start_learning": { "total": 488.8287806949993, "count": 1, "self": 0.6065480870856845, "children": { "TrainerController._reset_env": { "total": 5.072198931000457, "count": 1, "self": 5.072198931000457 }, "TrainerController.advance": { "total": 482.9976769819132, "count": 18215, "self": 0.3135042810226878, "children": { "env_step": { "total": 482.6841727008905, "count": 18215, "self": 329.7428118088865, "children": { "SubprocessEnvManager._take_step": { "total": 152.63644833307808, "count": 18215, "self": 2.010919573111096, "children": { "TorchPolicy.evaluate": { "total": 150.62552875996698, "count": 18215, "self": 150.62552875996698 } } }, "workers": { "total": 0.3049125589259347, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 487.00681764308683, "count": 18215, "is_parallel": true, "self": 217.11979806996897, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031566649995511398, "count": 1, "is_parallel": true, "self": 0.0008025640017876867, "children": { "_process_rank_one_or_two_observation": { "total": 0.002354100997763453, "count": 10, "is_parallel": true, "self": 0.002354100997763453 } } }, "UnityEnvironment.step": { "total": 0.0503288039999461, "count": 1, "is_parallel": true, "self": 0.00044396799967216793, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036525100040307734, "count": 1, "is_parallel": true, "self": 0.00036525100040307734 }, "communicator.exchange": { "total": 0.04633746699983021, "count": 1, "is_parallel": true, "self": 0.04633746699983021 }, "steps_from_proto": { "total": 0.0031821180000406457, "count": 1, "is_parallel": true, "self": 0.0013967680006317096, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017853499994089361, "count": 10, "is_parallel": true, "self": 0.0017853499994089361 } } } } } } }, "UnityEnvironment.step": { "total": 269.88701957311787, "count": 18214, "is_parallel": true, "self": 11.017855447158581, "children": { "UnityEnvironment._generate_step_input": { "total": 5.760899235985562, "count": 18214, "is_parallel": true, "self": 5.760899235985562 }, "communicator.exchange": { "total": 213.35939599697667, "count": 18214, "is_parallel": true, "self": 213.35939599697667 }, "steps_from_proto": { "total": 39.74886889299705, "count": 18214, "is_parallel": true, "self": 7.288212614084841, "children": { "_process_rank_one_or_two_observation": { "total": 32.46065627891221, "count": 182140, "is_parallel": true, "self": 32.46065627891221 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.9815999116399325e-05, "count": 1, "self": 3.9815999116399325e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 480.6060743708822, "count": 287816, "is_parallel": true, "self": 7.188309569088233, "children": { "process_trajectory": { "total": 171.0720139917994, "count": 287816, "is_parallel": true, "self": 170.23745129379859, "children": { "RLTrainer._checkpoint": { "total": 0.8345626980008092, "count": 4, "is_parallel": true, "self": 0.8345626980008092 } } }, "_update_policy": { "total": 302.34575080999457, "count": 90, "is_parallel": true, "self": 97.19458248201772, "children": { "TorchPPOOptimizer.update": { "total": 205.15116832797685, "count": 4590, "is_parallel": true, "self": 205.15116832797685 } } } } } } } } }, "TrainerController._save_models": { "total": 0.152316879000864, "count": 1, "self": 0.0010705269996833522, "children": { "RLTrainer._checkpoint": { "total": 0.15124635200118064, "count": 1, "self": 0.15124635200118064 } } } } } } }