{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403549313545227, "min": 1.403549313545227, "max": 1.4262654781341553, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72149.453125, "min": 67043.671875, "max": 77927.8046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.62118491921005, "min": 83.03865546218488, "max": 394.20472440944883, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49362.0, "min": 49270.0, "max": 50064.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999955.0, "min": 49828.0, "max": 1999955.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999955.0, "min": 49828.0, "max": 1999955.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4571170806884766, "min": 0.03554686903953552, "max": 2.5092613697052, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1368.6142578125, "min": 4.47890567779541, "max": 1435.1705322265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8436800581762562, "min": 1.816536073646848, "max": 4.04828308735575, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2140.929792404175, "min": 228.88354527950287, "max": 2274.8646979928017, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8436800581762562, "min": 1.816536073646848, "max": 4.04828308735575, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2140.929792404175, "min": 228.88354527950287, "max": 2274.8646979928017, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01717359405237302, "min": 0.013718947173523096, "max": 0.021417782385833563, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051520782157119055, "min": 0.02743789434704619, "max": 0.060525537555804476, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05908615282840199, "min": 0.022677835449576376, "max": 0.06256076999836498, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17725845848520597, "min": 0.04535567089915275, "max": 0.18768230999509494, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2679489107166715e-06, "min": 3.2679489107166715e-06, "max": 0.00029535075154974995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.803846732150014e-06, "min": 9.803846732150014e-06, "max": 0.0008441584686138498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10108928333333332, "min": 0.10108928333333332, "max": 0.19845025000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30326784999999995, "min": 0.20731555000000002, "max": 0.58138615, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.435523833333345e-05, "min": 6.435523833333345e-05, "max": 0.004922667475, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019306571500000034, "min": 0.00019306571500000034, "max": 0.014071168884999999, "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": "1675876480", "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": "1675879097" }, "total": 2617.164515026, "count": 1, "self": 0.4436467639998227, "children": { "run_training.setup": { "total": 0.17537624600004165, "count": 1, "self": 0.17537624600004165 }, "TrainerController.start_learning": { "total": 2616.545492016, "count": 1, "self": 5.374971191864461, "children": { "TrainerController._reset_env": { "total": 10.670484468999803, "count": 1, "self": 10.670484468999803 }, "TrainerController.advance": { "total": 2600.384051426135, "count": 232561, "self": 5.712457808873751, "children": { "env_step": { "total": 2032.2210394541655, "count": 232561, "self": 1693.1675479682372, "children": { "SubprocessEnvManager._take_step": { "total": 335.5636088590452, "count": 232561, "self": 17.87482982901838, "children": { "TorchPolicy.evaluate": { "total": 317.6887790300268, "count": 223079, "self": 81.16851569096184, "children": { "TorchPolicy.sample_actions": { "total": 236.52026333906497, "count": 223079, "self": 236.52026333906497 } } } } }, "workers": { "total": 3.4898826268831726, "count": 232561, "self": 0.0, "children": { "worker_root": { "total": 2606.5128298599857, "count": 232561, "is_parallel": true, "self": 1238.567619329001, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007232813999962673, "count": 1, "is_parallel": true, "self": 0.0006331869999485207, "children": { "_process_rank_one_or_two_observation": { "total": 0.006599627000014152, "count": 2, "is_parallel": true, "self": 0.006599627000014152 } } }, "UnityEnvironment.step": { "total": 0.030550535999964268, "count": 1, "is_parallel": true, "self": 0.00027675399996951455, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021829000002071552, "count": 1, "is_parallel": true, "self": 0.00021829000002071552 }, "communicator.exchange": { "total": 0.029312202000028265, "count": 1, "is_parallel": true, "self": 0.029312202000028265 }, "steps_from_proto": { "total": 0.0007432899999457732, "count": 1, "is_parallel": true, "self": 0.00023128700013330672, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005120029998124664, "count": 2, "is_parallel": true, "self": 0.0005120029998124664 } } } } } } }, "UnityEnvironment.step": { "total": 1367.9452105309847, "count": 232560, "is_parallel": true, "self": 40.388294782040475, "children": { "UnityEnvironment._generate_step_input": { "total": 80.02356977091881, "count": 232560, "is_parallel": true, "self": 80.02356977091881 }, "communicator.exchange": { "total": 1141.327361970937, "count": 232560, "is_parallel": true, "self": 1141.327361970937 }, "steps_from_proto": { "total": 106.20598400708832, "count": 232560, "is_parallel": true, "self": 40.84339003504647, "children": { "_process_rank_one_or_two_observation": { "total": 65.36259397204185, "count": 465120, "is_parallel": true, "self": 65.36259397204185 } } } } } } } } } } }, "trainer_advance": { "total": 562.4505541630958, "count": 232561, "self": 7.820878230869539, "children": { "process_trajectory": { "total": 168.01415811822585, "count": 232561, "self": 166.74025660522693, "children": { "RLTrainer._checkpoint": { "total": 1.2739015129989184, "count": 10, "self": 1.2739015129989184 } } }, "_update_policy": { "total": 386.61551781400044, "count": 97, "self": 325.8335821809951, "children": { "TorchPPOOptimizer.update": { "total": 60.78193563300533, "count": 2910, "self": 60.78193563300533 } } } } } } }, "trainer_threads": { "total": 8.739998520468362e-07, "count": 1, "self": 8.739998520468362e-07 }, "TrainerController._save_models": { "total": 0.11598405500080844, "count": 1, "self": 0.002315440000529634, "children": { "RLTrainer._checkpoint": { "total": 0.1136686150002788, "count": 1, "self": 0.1136686150002788 } } } } } } }