{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4615787267684937, "min": 1.4615787267684937, "max": 1.4631232023239136, "count": 21 }, "Huggy.Policy.Entropy.sum": { "value": 74242.3515625, "min": 1629.9193115234375, "max": 74497.140625, "count": 21 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.89409722222223, "min": 38.125, "max": 85.89409722222223, "count": 21 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49475.0, "min": 610.0, "max": 49955.0, "count": 21 }, "Huggy.Step.mean": { "value": 4999998.0, "min": 3999975.0, "max": 4999998.0, "count": 21 }, "Huggy.Step.sum": { "value": 4999998.0, "min": 3999975.0, "max": 4999998.0, "count": 21 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.529625415802002, "min": 2.0727760791778564, "max": 2.5629072189331055, "count": 21 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1457.064208984375, "min": 31.091642379760742, "max": 1960.6240234375, "count": 21 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9443130030607185, "min": 2.8365768909454347, "max": 4.030576722112218, "count": 21 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2271.924289762974, "min": 42.54865336418152, "max": 3056.473274052143, "count": 21 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9443130030607185, "min": 2.8365768909454347, "max": 4.030576722112218, "count": 21 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2271.924289762974, "min": 42.54865336418152, "max": 3056.473274052143, "count": 21 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 21 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 21 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01645280432494474, "min": 0.012763792780606308, "max": 0.01964172369625885, "count": 20 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03290560864988948, "min": 0.025527585561212617, "max": 0.05818501380088037, "count": 20 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0511211009696126, "min": 0.050411403831094506, "max": 0.06767749013379216, "count": 20 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1022422019392252, "min": 0.10082280766218901, "max": 0.18741850070655347, "count": 20 }, "Huggy.Policy.LearningRate.mean": { "value": 1.3346195551600054e-06, "min": 1.3346195551600054e-06, "max": 5.818682060442e-05, "count": 20 }, "Huggy.Policy.LearningRate.sum": { "value": 2.6692391103200107e-06, "min": 2.6692391103200107e-06, "max": 0.00015793068735651996, "count": 20 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10000000000000002, "min": 0.10000000000000002, "max": 0.10000000000000002, "count": 20 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20000000000000004, "min": 0.20000000000000004, "max": 0.30000000000000004, "count": 20 }, "Huggy.Policy.Beta.mean": { "value": 3.21975160000001e-05, "min": 3.21975160000001e-05, "max": 0.0009778394420000003, "count": 20 }, "Huggy.Policy.Beta.sum": { "value": 6.43950320000002e-05, "min": 6.43950320000002e-05, "max": 0.002656909652, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687614204", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687615397" }, "total": 1192.3650826270004, "count": 1, "self": 0.7867250870003772, "children": { "run_training.setup": { "total": 0.037453466999977536, "count": 1, "self": 0.037453466999977536 }, "TrainerController.start_learning": { "total": 1191.540904073, "count": 1, "self": 2.2832590788630114, "children": { "TrainerController._reset_env": { "total": 5.247246918000201, "count": 1, "self": 5.247246918000201 }, "TrainerController.advance": { "total": 1183.8228053371377, "count": 118227, "self": 2.377192093001213, "children": { "env_step": { "total": 969.1501620849649, "count": 118227, "self": 820.3189952230896, "children": { "SubprocessEnvManager._take_step": { "total": 147.4172532687835, "count": 118227, "self": 8.327659440872594, "children": { "TorchPolicy.evaluate": { "total": 139.0895938279109, "count": 111786, "self": 139.0895938279109 } } }, "workers": { "total": 1.41391359309182, "count": 118227, "self": 0.0, "children": { "worker_root": { "total": 1187.3567987089855, "count": 118227, "is_parallel": true, "self": 512.0929151738137, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007698909994360292, "count": 1, "is_parallel": true, "self": 0.00021642999945470365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005534609999813256, "count": 2, "is_parallel": true, "self": 0.0005534609999813256 } } }, "UnityEnvironment.step": { "total": 0.07165625600009662, "count": 1, "is_parallel": true, "self": 0.00032951399953162763, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022036300015315646, "count": 1, "is_parallel": true, "self": 0.00022036300015315646 }, "communicator.exchange": { "total": 0.07035627200002637, "count": 1, "is_parallel": true, "self": 0.07035627200002637 }, "steps_from_proto": { "total": 0.0007501070003854693, "count": 1, "is_parallel": true, "self": 0.00022152299970912281, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005285840006763465, "count": 2, "is_parallel": true, "self": 0.0005285840006763465 } } } } } } }, "UnityEnvironment.step": { "total": 675.2638835351718, "count": 118226, "is_parallel": true, "self": 19.8972707592402, "children": { "UnityEnvironment._generate_step_input": { "total": 40.74938854701486, "count": 118226, "is_parallel": true, "self": 40.74938854701486 }, "communicator.exchange": { "total": 565.1960905508777, "count": 118226, "is_parallel": true, "self": 565.1960905508777 }, "steps_from_proto": { "total": 49.42113367803904, "count": 118226, "is_parallel": true, "self": 17.638342123775146, "children": { "_process_rank_one_or_two_observation": { "total": 31.782791554263895, "count": 236452, "is_parallel": true, "self": 31.782791554263895 } } } } } } } } } } }, "trainer_advance": { "total": 212.29545115917153, "count": 118227, "self": 3.3879345521399955, "children": { "process_trajectory": { "total": 77.31324694803061, "count": 118227, "self": 76.35542192603043, "children": { "RLTrainer._checkpoint": { "total": 0.9578250220001792, "count": 6, "self": 0.9578250220001792 } } }, "_update_policy": { "total": 131.59426965900093, "count": 48, "self": 111.28623789800713, "children": { "TorchPPOOptimizer.update": { "total": 20.3080317609938, "count": 960, "self": 20.3080317609938 } } } } } } }, "trainer_threads": { "total": 1.4039997040526941e-06, "count": 1, "self": 1.4039997040526941e-06 }, "TrainerController._save_models": { "total": 0.1875913349995244, "count": 1, "self": 0.002902106999499665, "children": { "RLTrainer._checkpoint": { "total": 0.18468922800002474, "count": 1, "self": 0.18468922800002474 } } } } } } }