{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.89847731590271, "min": 0.89847731590271, "max": 2.8568453788757324, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8578.6611328125, "min": 8578.6611328125, "max": 29476.931640625, "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": 13.569844245910645, "min": 0.2653351128101349, "max": 13.569844245910645, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2646.11962890625, "min": 51.475013732910156, "max": 2761.402587890625, "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": 0.06668974088207513, "min": 0.06317610574588806, "max": 0.0718012741574638, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26675896352830053, "min": 0.25327943122976054, "max": 0.359006370787319, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19702466603900703, "min": 0.12991550370528435, "max": 0.3081792602080758, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7880986641560281, "min": 0.5196620148211374, "max": 1.2938558369123634, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.00029188200270599996, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.0013851600382799997, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999998, "min": 0.10269399999999998, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4107759999999999, "min": 0.4107759999999999, "max": 0.9617200000000001, "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": 26.454545454545453, "min": 4.295454545454546, "max": 26.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1164.0, "min": 189.0, "max": 1447.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.454545454545453, "min": 4.295454545454546, "max": 26.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1164.0, "min": 189.0, "max": 1447.0, "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": "1720697634", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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", "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": "1720698258" }, "total": 623.378830529, "count": 1, "self": 0.7622470869999916, "children": { "run_training.setup": { "total": 0.0634420640000144, "count": 1, "self": 0.0634420640000144 }, "TrainerController.start_learning": { "total": 622.553141378, "count": 1, "self": 0.6421735429959199, "children": { "TrainerController._reset_env": { "total": 3.116021412000009, "count": 1, "self": 3.116021412000009 }, "TrainerController.advance": { "total": 618.6599596710041, "count": 18204, "self": 0.3057048370033044, "children": { "env_step": { "total": 618.3542548340008, "count": 18204, "self": 452.25162394300656, "children": { "SubprocessEnvManager._take_step": { "total": 165.78010395500564, "count": 18204, "self": 1.5664254660080132, "children": { "TorchPolicy.evaluate": { "total": 164.21367848899763, "count": 18204, "self": 164.21367848899763 } } }, "workers": { "total": 0.3225269359886056, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 621.1860067020058, "count": 18204, "is_parallel": true, "self": 377.1664588190198, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059937610000133645, "count": 1, "is_parallel": true, "self": 0.004220195999948828, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017735650000645364, "count": 10, "is_parallel": true, "self": 0.0017735650000645364 } } }, "UnityEnvironment.step": { "total": 0.03914577599999802, "count": 1, "is_parallel": true, "self": 0.0007394009999757145, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046141199999283344, "count": 1, "is_parallel": true, "self": 0.00046141199999283344 }, "communicator.exchange": { "total": 0.0356963240000141, "count": 1, "is_parallel": true, "self": 0.0356963240000141 }, "steps_from_proto": { "total": 0.0022486390000153733, "count": 1, "is_parallel": true, "self": 0.0004368219999832945, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018118170000320788, "count": 10, "is_parallel": true, "self": 0.0018118170000320788 } } } } } } }, "UnityEnvironment.step": { "total": 244.019547882986, "count": 18203, "is_parallel": true, "self": 11.272314361987185, "children": { "UnityEnvironment._generate_step_input": { "total": 5.803166861997624, "count": 18203, "is_parallel": true, "self": 5.803166861997624 }, "communicator.exchange": { "total": 190.47379850399955, "count": 18203, "is_parallel": true, "self": 190.47379850399955 }, "steps_from_proto": { "total": 36.470268155001634, "count": 18203, "is_parallel": true, "self": 7.058214209006394, "children": { "_process_rank_one_or_two_observation": { "total": 29.41205394599524, "count": 182030, "is_parallel": true, "self": 29.41205394599524 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001674950000278841, "count": 1, "self": 0.0001674950000278841, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 612.5495153380015, "count": 713057, "is_parallel": true, "self": 15.902644685015161, "children": { "process_trajectory": { "total": 252.02796694698645, "count": 713057, "is_parallel": true, "self": 250.8213654939865, "children": { "RLTrainer._checkpoint": { "total": 1.206601452999962, "count": 4, "is_parallel": true, "self": 1.206601452999962 } } }, "_update_policy": { "total": 344.6189037059999, "count": 90, "is_parallel": true, "self": 138.09834708999608, "children": { "TorchPPOOptimizer.update": { "total": 206.52055661600383, "count": 10696, "is_parallel": true, "self": 206.52055661600383 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13481925699989006, "count": 1, "self": 0.001396865999822694, "children": { "RLTrainer._checkpoint": { "total": 0.13342239100006736, "count": 1, "self": 0.13342239100006736 } } } } } } }