{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.401172399520874, "min": 1.401172399520874, "max": 1.4244650602340698, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70260.390625, "min": 68942.1953125, "max": 75767.328125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.37421383647799, "min": 77.37421383647799, "max": 412.1639344262295, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49210.0, "min": 49210.0, "max": 50284.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999998.0, "min": 49896.0, "max": 1999998.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999998.0, "min": 49896.0, "max": 1999998.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.446917772293091, "min": 0.04072913900017738, "max": 2.467331647872925, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1556.23974609375, "min": 4.928225994110107, "max": 1556.23974609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.784534518823684, "min": 1.8800790351777037, "max": 3.9365997119737406, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2406.963953971863, "min": 227.48956325650215, "max": 2420.4665558338165, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.784534518823684, "min": 1.8800790351777037, "max": 3.9365997119737406, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2406.963953971863, "min": 227.48956325650215, "max": 2420.4665558338165, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017268840475177665, "min": 0.013497869887699684, "max": 0.019788790604798122, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05180652142553299, "min": 0.026995739775399367, "max": 0.05819971584714949, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0563753742724657, "min": 0.02256446685642004, "max": 0.05884254407137632, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1691261228173971, "min": 0.04512893371284008, "max": 0.1691261228173971, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.705048765016674e-06, "min": 3.705048765016674e-06, "max": 0.00029532577655807493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1115146295050023e-05, "min": 1.1115146295050023e-05, "max": 0.0008439994686668499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123498333333332, "min": 0.10123498333333332, "max": 0.19844192500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30370495, "min": 0.20760685, "max": 0.58133315, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.162566833333344e-05, "min": 7.162566833333344e-05, "max": 0.0049222520575000015, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021487700500000031, "min": 0.00021487700500000031, "max": 0.014068524185000004, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677011173", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1677013692" }, "total": 2519.053446174, "count": 1, "self": 0.3894274959998256, "children": { "run_training.setup": { "total": 0.17319067599999016, "count": 1, "self": 0.17319067599999016 }, "TrainerController.start_learning": { "total": 2518.490828002, "count": 1, "self": 4.45730224906174, "children": { "TrainerController._reset_env": { "total": 10.106033335999996, "count": 1, "self": 10.106033335999996 }, "TrainerController.advance": { "total": 2503.8062585269377, "count": 232676, "self": 4.774243862947969, "children": { "env_step": { "total": 1956.6934185860355, "count": 232676, "self": 1627.8872891868953, "children": { "SubprocessEnvManager._take_step": { "total": 325.81780685607976, "count": 232676, "self": 16.557656853099957, "children": { "TorchPolicy.evaluate": { "total": 309.2601500029798, "count": 222899, "self": 76.58235212607849, "children": { "TorchPolicy.sample_actions": { "total": 232.6777978769013, "count": 222899, "self": 232.6777978769013 } } } } }, "workers": { "total": 2.9883225430604625, "count": 232676, "self": 0.0, "children": { "worker_root": { "total": 2509.7282723261405, "count": 232676, "is_parallel": true, "self": 1186.2148545071464, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002331907999973737, "count": 1, "is_parallel": true, "self": 0.00045572899989565485, "children": { "_process_rank_one_or_two_observation": { "total": 0.001876179000078082, "count": 2, "is_parallel": true, "self": 0.001876179000078082 } } }, "UnityEnvironment.step": { "total": 0.031291925000004994, "count": 1, "is_parallel": true, "self": 0.00028642799998124246, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024009599997043551, "count": 1, "is_parallel": true, "self": 0.00024009599997043551 }, "communicator.exchange": { "total": 0.029877315000021554, "count": 1, "is_parallel": true, "self": 0.029877315000021554 }, "steps_from_proto": { "total": 0.0008880860000317625, "count": 1, "is_parallel": true, "self": 0.0004174000000602973, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004706859999714652, "count": 2, "is_parallel": true, "self": 0.0004706859999714652 } } } } } } }, "UnityEnvironment.step": { "total": 1323.5134178189942, "count": 232675, "is_parallel": true, "self": 39.11053549211874, "children": { "UnityEnvironment._generate_step_input": { "total": 83.76967654895407, "count": 232675, "is_parallel": true, "self": 83.76967654895407 }, "communicator.exchange": { "total": 1103.7073983470414, "count": 232675, "is_parallel": true, "self": 1103.7073983470414 }, "steps_from_proto": { "total": 96.92580743088001, "count": 232675, "is_parallel": true, "self": 41.49018166604685, "children": { "_process_rank_one_or_two_observation": { "total": 55.43562576483316, "count": 465350, "is_parallel": true, "self": 55.43562576483316 } } } } } } } } } } }, "trainer_advance": { "total": 542.3385960779544, "count": 232676, "self": 6.796796170001812, "children": { "process_trajectory": { "total": 174.79646034695293, "count": 232676, "self": 173.5269584799529, "children": { "RLTrainer._checkpoint": { "total": 1.2695018670000309, "count": 10, "self": 1.2695018670000309 } } }, "_update_policy": { "total": 360.7453395609997, "count": 97, "self": 302.9970450170051, "children": { "TorchPPOOptimizer.update": { "total": 57.748294543994575, "count": 2910, "self": 57.748294543994575 } } } } } } }, "trainer_threads": { "total": 8.260003596660681e-07, "count": 1, "self": 8.260003596660681e-07 }, "TrainerController._save_models": { "total": 0.12123306400008005, "count": 1, "self": 0.002057405999948969, "children": { "RLTrainer._checkpoint": { "total": 0.11917565800013108, "count": 1, "self": 0.11917565800013108 } } } } } } }