{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4094297885894775, "min": 1.4094297885894775, "max": 1.4300824403762817, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71083.1796875, "min": 68008.1875, "max": 77948.6875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.94360902255639, "min": 80.72249589490968, "max": 408.609756097561, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49446.0, "min": 48825.0, "max": 50259.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999952.0, "min": 49930.0, "max": 1999952.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999952.0, "min": 49930.0, "max": 1999952.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4642529487609863, "min": 0.08819211274385452, "max": 2.4748287200927734, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1310.9825439453125, "min": 10.759437561035156, "max": 1486.62158203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.843432180863574, "min": 1.9168427115092512, "max": 3.969630683843906, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2044.7059202194214, "min": 233.85481080412865, "max": 2332.430609345436, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.843432180863574, "min": 1.9168427115092512, "max": 3.969630683843906, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2044.7059202194214, "min": 233.85481080412865, "max": 2332.430609345436, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014273935747203521, "min": 0.014273935747203521, "max": 0.02019394244804668, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04282180724161056, "min": 0.02977414053166285, "max": 0.05455490564636421, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05961300167772505, "min": 0.02214867395038406, "max": 0.06421136396626631, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17883900503317515, "min": 0.04429734790076812, "max": 0.1832060938080152, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6048487984166673e-06, "min": 3.6048487984166673e-06, "max": 0.00029527905157364994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0814546395250002e-05, "min": 1.0814546395250002e-05, "max": 0.0008439474186841999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120158333333333, "min": 0.10120158333333333, "max": 0.19842635000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30360475, "min": 0.20753690000000002, "max": 0.5813158, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.995900833333336e-05, "min": 6.995900833333336e-05, "max": 0.004921474865000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020987702500000009, "min": 0.00020987702500000009, "max": 0.014067658420000004, "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": "1671543023", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1671545227" }, "total": 2203.098993009, "count": 1, "self": 0.4410756110000875, "children": { "run_training.setup": { "total": 0.10686310100004448, "count": 1, "self": 0.10686310100004448 }, "TrainerController.start_learning": { "total": 2202.551054297, "count": 1, "self": 3.7809863619750104, "children": { "TrainerController._reset_env": { "total": 7.48850744899994, "count": 1, "self": 7.48850744899994 }, "TrainerController.advance": { "total": 2191.167232867025, "count": 232653, "self": 3.8527108599500934, "children": { "env_step": { "total": 1721.4894948390147, "count": 232653, "self": 1447.2082196190554, "children": { "SubprocessEnvManager._take_step": { "total": 271.76867531812445, "count": 232653, "self": 14.044532142149137, "children": { "TorchPolicy.evaluate": { "total": 257.7241431759753, "count": 222954, "self": 64.91530438591417, "children": { "TorchPolicy.sample_actions": { "total": 192.80883879006115, "count": 222954, "self": 192.80883879006115 } } } } }, "workers": { "total": 2.5125999018348466, "count": 232653, "self": 0.0, "children": { "worker_root": { "total": 2194.915919880904, "count": 232653, "is_parallel": true, "self": 1001.3887619309153, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002053421000027811, "count": 1, "is_parallel": true, "self": 0.00032636800006002886, "children": { "_process_rank_one_or_two_observation": { "total": 0.001727052999967782, "count": 2, "is_parallel": true, "self": 0.001727052999967782 } } }, "UnityEnvironment.step": { "total": 0.0274623770000062, "count": 1, "is_parallel": true, "self": 0.00028014500014705845, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001682700000174009, "count": 1, "is_parallel": true, "self": 0.0001682700000174009 }, "communicator.exchange": { "total": 0.026322088999904736, "count": 1, "is_parallel": true, "self": 0.026322088999904736 }, "steps_from_proto": { "total": 0.0006918729999370044, "count": 1, "is_parallel": true, "self": 0.0002400559999387042, "children": { "_process_rank_one_or_two_observation": { "total": 0.00045181699999830016, "count": 2, "is_parallel": true, "self": 0.00045181699999830016 } } } } } } }, "UnityEnvironment.step": { "total": 1193.5271579499886, "count": 232652, "is_parallel": true, "self": 34.71241564194952, "children": { "UnityEnvironment._generate_step_input": { "total": 75.37772521513057, "count": 232652, "is_parallel": true, "self": 75.37772521513057 }, "communicator.exchange": { "total": 990.5407556930146, "count": 232652, "is_parallel": true, "self": 990.5407556930146 }, "steps_from_proto": { "total": 92.89626139989389, "count": 232652, "is_parallel": true, "self": 38.116709800943, "children": { "_process_rank_one_or_two_observation": { "total": 54.77955159895089, "count": 465304, "is_parallel": true, "self": 54.77955159895089 } } } } } } } } } } }, "trainer_advance": { "total": 465.8250271680604, "count": 232653, "self": 5.725262491069202, "children": { "process_trajectory": { "total": 146.57509986499144, "count": 232653, "self": 145.26180925699157, "children": { "RLTrainer._checkpoint": { "total": 1.3132906079998747, "count": 10, "self": 1.3132906079998747 } } }, "_update_policy": { "total": 313.52466481199974, "count": 97, "self": 260.84644420699954, "children": { "TorchPPOOptimizer.update": { "total": 52.678220605000206, "count": 2910, "self": 52.678220605000206 } } } } } } }, "trainer_threads": { "total": 1.0680000741558615e-06, "count": 1, "self": 1.0680000741558615e-06 }, "TrainerController._save_models": { "total": 0.11432655099997646, "count": 1, "self": 0.0019319009998071124, "children": { "RLTrainer._checkpoint": { "total": 0.11239465000016935, "count": 1, "self": 0.11239465000016935 } } } } } } }