{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4074312448501587, "min": 1.4074312448501587, "max": 1.4272277355194092, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68847.3125, "min": 66963.3203125, "max": 77696.859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.7600806451613, "min": 84.34982935153583, "max": 439.0173913043478, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49481.0, "min": 48997.0, "max": 50487.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999271.0, "min": 49991.0, "max": 1999271.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999271.0, "min": 49991.0, "max": 1999271.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4386324882507324, "min": -0.06875632703304291, "max": 2.4781606197357178, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1209.561767578125, "min": -7.838221073150635, "max": 1415.818115234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.764980227956849, "min": 1.6008196243068629, "max": 3.978435402525995, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1867.430193066597, "min": 182.49343717098236, "max": 2239.5351192355156, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.764980227956849, "min": 1.6008196243068629, "max": 3.978435402525995, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1867.430193066597, "min": 182.49343717098236, "max": 2239.5351192355156, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017641928240320542, "min": 0.014119155321532162, "max": 0.01879551256230722, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05292578472096163, "min": 0.028238310643064323, "max": 0.05396191006584558, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053334762280186014, "min": 0.024126149713993073, "max": 0.05964861719144715, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16000428684055804, "min": 0.048252299427986145, "max": 0.17894585157434145, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.286548904516675e-06, "min": 3.286548904516675e-06, "max": 0.00029535465154845, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.859646713550025e-06, "min": 9.859646713550025e-06, "max": 0.0008440081686639498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109548333333333, "min": 0.10109548333333333, "max": 0.19845154999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30328645, "min": 0.20737294999999997, "max": 0.58133605, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.466461833333347e-05, "min": 6.466461833333347e-05, "max": 0.004922732345, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001939938550000004, "min": 0.0001939938550000004, "max": 0.014068668894999997, "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": "1700387578", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700390115" }, "total": 2536.97941747, "count": 1, "self": 0.6497640229999888, "children": { "run_training.setup": { "total": 0.04907023400005528, "count": 1, "self": 0.04907023400005528 }, "TrainerController.start_learning": { "total": 2536.2805832129998, "count": 1, "self": 4.823916745954193, "children": { "TrainerController._reset_env": { "total": 9.076823856000033, "count": 1, "self": 9.076823856000033 }, "TrainerController.advance": { "total": 2522.236271335046, "count": 232095, "self": 4.849155064162005, "children": { "env_step": { "total": 2011.2948978289237, "count": 232095, "self": 1658.045180706717, "children": { "SubprocessEnvManager._take_step": { "total": 350.2803926861267, "count": 232095, "self": 17.34090378709334, "children": { "TorchPolicy.evaluate": { "total": 332.93948889903334, "count": 222912, "self": 332.93948889903334 } } }, "workers": { "total": 2.969324436079887, "count": 232095, "self": 0.0, "children": { "worker_root": { "total": 2528.4968680909683, "count": 232095, "is_parallel": true, "self": 1184.0837947140456, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008542589999933625, "count": 1, "is_parallel": true, "self": 0.0002762799999800336, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005779790000133289, "count": 2, "is_parallel": true, "self": 0.0005779790000133289 } } }, "UnityEnvironment.step": { "total": 0.04859530600003836, "count": 1, "is_parallel": true, "self": 0.00033692099998461345, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019839900005536037, "count": 1, "is_parallel": true, "self": 0.00019839900005536037 }, "communicator.exchange": { "total": 0.04727216399999179, "count": 1, "is_parallel": true, "self": 0.04727216399999179 }, "steps_from_proto": { "total": 0.0007878220000065994, "count": 1, "is_parallel": true, "self": 0.00030846500010284217, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047935699990375724, "count": 2, "is_parallel": true, "self": 0.00047935699990375724 } } } } } } }, "UnityEnvironment.step": { "total": 1344.4130733769227, "count": 232094, "is_parallel": true, "self": 40.630177832104664, "children": { "UnityEnvironment._generate_step_input": { "total": 86.17548197085682, "count": 232094, "is_parallel": true, "self": 86.17548197085682 }, "communicator.exchange": { "total": 1126.1786118119671, "count": 232094, "is_parallel": true, "self": 1126.1786118119671 }, "steps_from_proto": { "total": 91.42880176199435, "count": 232094, "is_parallel": true, "self": 34.10207872889373, "children": { "_process_rank_one_or_two_observation": { "total": 57.32672303310062, "count": 464188, "is_parallel": true, "self": 57.32672303310062 } } } } } } } } } } }, "trainer_advance": { "total": 506.0922184419601, "count": 232095, "self": 7.0936761959104615, "children": { "process_trajectory": { "total": 162.22919933504886, "count": 232095, "self": 161.08494226604876, "children": { "RLTrainer._checkpoint": { "total": 1.1442570690001048, "count": 10, "self": 1.1442570690001048 } } }, "_update_policy": { "total": 336.76934291100076, "count": 97, "self": 274.90194351999423, "children": { "TorchPPOOptimizer.update": { "total": 61.86739939100653, "count": 2910, "self": 61.86739939100653 } } } } } } }, "trainer_threads": { "total": 1.416000031895237e-06, "count": 1, "self": 1.416000031895237e-06 }, "TrainerController._save_models": { "total": 0.14356985999984317, "count": 1, "self": 0.0025695099998301885, "children": { "RLTrainer._checkpoint": { "total": 0.141000350000013, "count": 1, "self": 0.141000350000013 } } } } } } }