{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0046346187591553, "min": 0.9967865347862244, "max": 2.8758511543273926, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9382.283203125, "min": 9382.283203125, "max": 30122.2734375, "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": 12.767321586608887, "min": 0.38611656427383423, "max": 12.767321586608887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1289.49951171875, "min": 37.45330810546875, "max": 1289.49951171875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.192307692307693, "min": 3.477272727272727, "max": 25.306122448979593, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1310.0, "min": 153.0, "max": 1322.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.192307692307693, "min": 3.477272727272727, "max": 25.306122448979593, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1310.0, "min": 153.0, "max": 1322.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06890547062971118, "min": 0.06301052455862245, "max": 0.07725672581488172, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27562188251884473, "min": 0.25479822087686, "max": 0.38628362907440855, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2220799277956579, "min": 0.1350260905410145, "max": 0.30346141229657564, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8883197111826316, "min": 0.540104362164058, "max": 1.4412399948227639, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.950097350000008e-06, "min": 7.950097350000008e-06, "max": 0.00029175000274999995, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.180038940000003e-05, "min": 3.180038940000003e-05, "max": 0.0013845000385, "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": "1680537782", "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": "1680538221" }, "total": 439.2914376570001, "count": 1, "self": 0.7649324970001317, "children": { "run_training.setup": { "total": 0.10823584000002029, "count": 1, "self": 0.10823584000002029 }, "TrainerController.start_learning": { "total": 438.4182693199999, "count": 1, "self": 0.5580009460093152, "children": { "TrainerController._reset_env": { "total": 3.844960981999975, "count": 1, "self": 3.844960981999975 }, "TrainerController.advance": { "total": 433.77451306199055, "count": 18236, "self": 0.27848197999662716, "children": { "env_step": { "total": 433.4960310819939, "count": 18236, "self": 299.6102477089843, "children": { "SubprocessEnvManager._take_step": { "total": 133.61529429000495, "count": 18236, "self": 1.618926077013839, "children": { "TorchPolicy.evaluate": { "total": 131.99636821299111, "count": 18236, "self": 131.99636821299111 } } }, "workers": { "total": 0.27048908300469066, "count": 18236, "self": 0.0, "children": { "worker_root": { "total": 436.93340776199034, "count": 18236, "is_parallel": true, "self": 190.10911947598754, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0062341469999864785, "count": 1, "is_parallel": true, "self": 0.0047557399998368055, "children": { "_process_rank_one_or_two_observation": { "total": 0.001478407000149673, "count": 10, "is_parallel": true, "self": 0.001478407000149673 } } }, "UnityEnvironment.step": { "total": 0.04755781300002582, "count": 1, "is_parallel": true, "self": 0.0005674989999988611, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004523170000538812, "count": 1, "is_parallel": true, "self": 0.0004523170000538812 }, "communicator.exchange": { "total": 0.04480465400001776, "count": 1, "is_parallel": true, "self": 0.04480465400001776 }, "steps_from_proto": { "total": 0.0017333429999553118, "count": 1, "is_parallel": true, "self": 0.0003897759999063055, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013435670000490063, "count": 10, "is_parallel": true, "self": 0.0013435670000490063 } } } } } } }, "UnityEnvironment.step": { "total": 246.8242882860028, "count": 18235, "is_parallel": true, "self": 9.89520613799641, "children": { "UnityEnvironment._generate_step_input": { "total": 5.415324099000145, "count": 18235, "is_parallel": true, "self": 5.415324099000145 }, "communicator.exchange": { "total": 199.82442040800242, "count": 18235, "is_parallel": true, "self": 199.82442040800242 }, "steps_from_proto": { "total": 31.689337641003817, "count": 18235, "is_parallel": true, "self": 6.249747976026242, "children": { "_process_rank_one_or_two_observation": { "total": 25.439589664977575, "count": 182350, "is_parallel": true, "self": 25.439589664977575 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015710800005308556, "count": 1, "self": 0.00015710800005308556, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.3828814889757, "count": 199460, "is_parallel": true, "self": 4.951661548969241, "children": { "process_trajectory": { "total": 142.63325149600655, "count": 199460, "is_parallel": true, "self": 141.2521642450066, "children": { "RLTrainer._checkpoint": { "total": 1.38108725099994, "count": 4, "is_parallel": true, "self": 1.38108725099994 } } }, "_update_policy": { "total": 284.79796844399993, "count": 90, "is_parallel": true, "self": 81.80369195800256, "children": { "TorchPPOOptimizer.update": { "total": 202.99427648599737, "count": 4590, "is_parallel": true, "self": 202.99427648599737 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24063722200003212, "count": 1, "self": 0.001877223000064987, "children": { "RLTrainer._checkpoint": { "total": 0.23875999899996714, "count": 1, "self": 0.23875999899996714 } } } } } } }