{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.6395481824874878, "min": 1.6395481824874878, "max": 2.8564162254333496, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 16736.5078125, "min": 16736.5078125, "max": 29441.08203125, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.185148239135742, "min": 0.4165266454219818, "max": 8.185148239135742, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1669.770263671875, "min": 80.80616760253906, "max": 1669.770263671875, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06609853671594892, "min": 0.06154232791998178, "max": 0.07377701656214947, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33049268357974465, "min": 0.2579160844564766, "max": 0.35723233786320274, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2254839167875402, "min": 0.13958177042613718, "max": 0.2657166821115157, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.127419583937701, "min": 0.5583270817045487, "max": 1.3285834105575787, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 17.763636363636362, "min": 3.659090909090909, "max": 17.763636363636362, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 977.0, "min": 161.0, "max": 977.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 17.763636363636362, "min": 3.659090909090909, "max": 17.763636363636362, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 977.0, "min": 161.0, "max": 977.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678974684", "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": "1678974915" }, "total": 231.72714404600003, "count": 1, "self": 0.43015521300003456, "children": { "run_training.setup": { "total": 0.10267839799996636, "count": 1, "self": 0.10267839799996636 }, "TrainerController.start_learning": { "total": 231.19431043500003, "count": 1, "self": 0.28420954900218476, "children": { "TrainerController._reset_env": { "total": 8.725130409999906, "count": 1, "self": 8.725130409999906 }, "TrainerController.advance": { "total": 222.05590402599785, "count": 9137, "self": 0.14012065399799667, "children": { "env_step": { "total": 221.91578337199985, "count": 9137, "self": 161.63861024099265, "children": { "SubprocessEnvManager._take_step": { "total": 60.13953969100032, "count": 9137, "self": 0.9036570289957808, "children": { "TorchPolicy.evaluate": { "total": 59.23588266200454, "count": 9137, "self": 59.23588266200454 } } }, "workers": { "total": 0.13763344000687994, "count": 9137, "self": 0.0, "children": { "worker_root": { "total": 230.49218445699955, "count": 9137, "is_parallel": true, "self": 112.1439208249983, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006184263000022838, "count": 1, "is_parallel": true, "self": 0.004136266999921645, "children": { "_process_rank_one_or_two_observation": { "total": 0.002047996000101193, "count": 10, "is_parallel": true, "self": 0.002047996000101193 } } }, "UnityEnvironment.step": { "total": 0.03730256799997278, "count": 1, "is_parallel": true, "self": 0.0003904319999037398, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003292760000022099, "count": 1, "is_parallel": true, "self": 0.0003292760000022099 }, "communicator.exchange": { "total": 0.03493792200004009, "count": 1, "is_parallel": true, "self": 0.03493792200004009 }, "steps_from_proto": { "total": 0.001644938000026741, "count": 1, "is_parallel": true, "self": 0.0003359729997782779, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013089650002484632, "count": 10, "is_parallel": true, "self": 0.0013089650002484632 } } } } } } }, "UnityEnvironment.step": { "total": 118.34826363200125, "count": 9136, "is_parallel": true, "self": 4.6598411970014695, "children": { "UnityEnvironment._generate_step_input": { "total": 2.5773885869973583, "count": 9136, "is_parallel": true, "self": 2.5773885869973583 }, "communicator.exchange": { "total": 96.12857439599622, "count": 9136, "is_parallel": true, "self": 96.12857439599622 }, "steps_from_proto": { "total": 14.982459452006196, "count": 9136, "is_parallel": true, "self": 2.9818330040078536, "children": { "_process_rank_one_or_two_observation": { "total": 12.000626447998343, "count": 91360, "is_parallel": true, "self": 12.000626447998343 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000274155000056453, "count": 1, "self": 0.000274155000056453, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 220.58801289596852, "count": 191925, "is_parallel": true, "self": 4.598340775951215, "children": { "process_trajectory": { "total": 121.84949192101749, "count": 191925, "is_parallel": true, "self": 121.04439630601746, "children": { "RLTrainer._checkpoint": { "total": 0.8050956150000275, "count": 2, "is_parallel": true, "self": 0.8050956150000275 } } }, "_update_policy": { "total": 94.14018019899981, "count": 45, "is_parallel": true, "self": 35.38208663899843, "children": { "TorchPPOOptimizer.update": { "total": 58.758093560001385, "count": 2289, "is_parallel": true, "self": 58.758093560001385 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1287922950000393, "count": 1, "self": 0.0009033990000943959, "children": { "RLTrainer._checkpoint": { "total": 0.1278888959999449, "count": 1, "self": 0.1278888959999449 } } } } } } }