{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8405592441558838, "min": 0.8373939990997314, "max": 2.84542179107666, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7988.6748046875, "min": 7988.6748046875, "max": 29046.06640625, "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": 12.864789962768555, "min": 0.3364710211753845, "max": 12.991369247436523, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2508.634033203125, "min": 65.27537536621094, "max": 2650.2392578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0682292451150644, "min": 0.06199731983851604, "max": 0.0733750437872539, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2729169804602576, "min": 0.2627522991241159, "max": 0.3668752189362695, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23598498179047717, "min": 0.1302213026005227, "max": 0.30071586779519627, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9439399271619087, "min": 0.5208852104020908, "max": 1.5035793389759813, "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.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.Environment.CumulativeReward.mean": { "value": 25.113636363636363, "min": 3.090909090909091, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 136.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.090909090909091, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 136.0, "max": 1406.0, "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": "1793143418", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/content/mlagents-py310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1793143824" }, "total": 405.85419486499995, "count": 1, "self": 0.4271369649999315, "children": { "run_training.setup": { "total": 0.020157742000037615, "count": 1, "self": 0.020157742000037615 }, "TrainerController.start_learning": { "total": 405.406900158, "count": 1, "self": 0.3278668569969341, "children": { "TrainerController._reset_env": { "total": 1.8949481680000417, "count": 1, "self": 1.8949481680000417 }, "TrainerController.advance": { "total": 403.098011363003, "count": 18192, "self": 0.3695676280107705, "children": { "env_step": { "total": 294.61345369799585, "count": 18192, "self": 233.86332565399113, "children": { "SubprocessEnvManager._take_step": { "total": 60.5475346439996, "count": 18192, "self": 1.2740811639945946, "children": { "TorchPolicy.evaluate": { "total": 59.273453480005, "count": 18192, "self": 59.273453480005 } } }, "workers": { "total": 0.20259340000512793, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 404.5200107559967, "count": 18192, "is_parallel": true, "self": 198.19122363899805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022992500000214022, "count": 1, "is_parallel": true, "self": 0.0007286599999929422, "children": { "_process_rank_one_or_two_observation": { "total": 0.00157059000002846, "count": 10, "is_parallel": true, "self": 0.00157059000002846 } } }, "UnityEnvironment.step": { "total": 0.036997951999978795, "count": 1, "is_parallel": true, "self": 0.0006840329999704409, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004003029999921637, "count": 1, "is_parallel": true, "self": 0.0004003029999921637 }, "communicator.exchange": { "total": 0.033784067999988565, "count": 1, "is_parallel": true, "self": 0.033784067999988565 }, "steps_from_proto": { "total": 0.0021295480000276257, "count": 1, "is_parallel": true, "self": 0.0004007950000186611, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017287530000089646, "count": 10, "is_parallel": true, "self": 0.0017287530000089646 } } } } } } }, "UnityEnvironment.step": { "total": 206.32878711699863, "count": 18191, "is_parallel": true, "self": 10.889425301999722, "children": { "UnityEnvironment._generate_step_input": { "total": 5.414011236000022, "count": 18191, "is_parallel": true, "self": 5.414011236000022 }, "communicator.exchange": { "total": 154.481776309007, "count": 18191, "is_parallel": true, "self": 154.481776309007 }, "steps_from_proto": { "total": 35.54357426999189, "count": 18191, "is_parallel": true, "self": 6.214287202002481, "children": { "_process_rank_one_or_two_observation": { "total": 29.329287067989412, "count": 181910, "is_parallel": true, "self": 29.329287067989412 } } } } } } } } } } }, "trainer_advance": { "total": 108.1149900369964, "count": 18192, "self": 0.4376238739856717, "children": { "process_trajectory": { "total": 25.454688655011466, "count": 18192, "self": 25.05520016401141, "children": { "RLTrainer._checkpoint": { "total": 0.39948849100005646, "count": 4, "self": 0.39948849100005646 } } }, "_update_policy": { "total": 82.22267750799926, "count": 90, "self": 35.3991968739968, "children": { "TorchPPOOptimizer.update": { "total": 46.823480634002465, "count": 4587, "self": 46.823480634002465 } } } } } } }, "trainer_threads": { "total": 9.58999976319319e-07, "count": 1, "self": 9.58999976319319e-07 }, "TrainerController._save_models": { "total": 0.08607281100000819, "count": 1, "self": 0.000672112000074776, "children": { "RLTrainer._checkpoint": { "total": 0.08540069899993341, "count": 1, "self": 0.08540069899993341 } } } } } } }