{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4038923978805542, "min": 1.4038923978805542, "max": 1.430087924003601, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70111.7890625, "min": 68429.484375, "max": 79294.96875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 108.37855579868709, "min": 85.31533101045297, "max": 400.3888888888889, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49529.0, "min": 48971.0, "max": 50449.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999532.0, "min": 49916.0, "max": 1999532.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999532.0, "min": 49916.0, "max": 1999532.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3512637615203857, "min": 0.1344415694475174, "max": 2.422147035598755, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1074.527587890625, "min": 16.80519676208496, "max": 1369.00244140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.609942781455668, "min": 1.929640699148178, "max": 3.8624280621759763, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1649.7438511252403, "min": 241.20508739352226, "max": 2167.038027346134, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.609942781455668, "min": 1.929640699148178, "max": 3.8624280621759763, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1649.7438511252403, "min": 241.20508739352226, "max": 2167.038027346134, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014613893148230597, "min": 0.0123652809173412, "max": 0.02031189067573804, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04384167944469179, "min": 0.0247305618346824, "max": 0.06093567202721412, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04954227449165451, "min": 0.020298454848428567, "max": 0.06071181719501813, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14862682347496353, "min": 0.040596909696857135, "max": 0.16950150852402052, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3743488752500005e-06, "min": 3.3743488752500005e-06, "max": 0.0002953606515464499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0123046625750001e-05, "min": 1.0123046625750001e-05, "max": 0.0008443657685447498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112475, "min": 0.10112475, "max": 0.19845355, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30337425, "min": 0.20740675000000003, "max": 0.5814552500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.6125025e-05, "min": 6.6125025e-05, "max": 0.004922832145, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000198375075, "min": 0.000198375075, "max": 0.014074616975000002, "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": "1676374250", "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": "1676376744" }, "total": 2494.47160133, "count": 1, "self": 0.4416952259998652, "children": { "run_training.setup": { "total": 0.11873501699994904, "count": 1, "self": 0.11873501699994904 }, "TrainerController.start_learning": { "total": 2493.911171087, "count": 1, "self": 4.510901194001235, "children": { "TrainerController._reset_env": { "total": 10.589457094000068, "count": 1, "self": 10.589457094000068 }, "TrainerController.advance": { "total": 2478.6935687019986, "count": 231672, "self": 4.5854351409384435, "children": { "env_step": { "total": 1933.1873268450208, "count": 231672, "self": 1613.694657007066, "children": { "SubprocessEnvManager._take_step": { "total": 316.5626814599675, "count": 231672, "self": 16.0297840849222, "children": { "TorchPolicy.evaluate": { "total": 300.5328973750453, "count": 222997, "self": 74.63434062591978, "children": { "TorchPolicy.sample_actions": { "total": 225.89855674912553, "count": 222997, "self": 225.89855674912553 } } } } }, "workers": { "total": 2.929988377987229, "count": 231672, "self": 0.0, "children": { "worker_root": { "total": 2485.037331834195, "count": 231672, "is_parallel": true, "self": 1174.2031708331524, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005779372000006333, "count": 1, "is_parallel": true, "self": 0.0003949890001422318, "children": { "_process_rank_one_or_two_observation": { "total": 0.005384382999864101, "count": 2, "is_parallel": true, "self": 0.005384382999864101 } } }, "UnityEnvironment.step": { "total": 0.030352399999969748, "count": 1, "is_parallel": true, "self": 0.0003016459999116705, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023038200004066312, "count": 1, "is_parallel": true, "self": 0.00023038200004066312 }, "communicator.exchange": { "total": 0.028966486000058467, "count": 1, "is_parallel": true, "self": 0.028966486000058467 }, "steps_from_proto": { "total": 0.0008538859999589477, "count": 1, "is_parallel": true, "self": 0.00025311300009889237, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006007729998600553, "count": 2, "is_parallel": true, "self": 0.0006007729998600553 } } } } } } }, "UnityEnvironment.step": { "total": 1310.8341610010425, "count": 231671, "is_parallel": true, "self": 39.303181729871994, "children": { "UnityEnvironment._generate_step_input": { "total": 81.15272567310285, "count": 231671, "is_parallel": true, "self": 81.15272567310285 }, "communicator.exchange": { "total": 1095.0657135769857, "count": 231671, "is_parallel": true, "self": 1095.0657135769857 }, "steps_from_proto": { "total": 95.3125400210821, "count": 231671, "is_parallel": true, "self": 38.75461774800931, "children": { "_process_rank_one_or_two_observation": { "total": 56.55792227307279, "count": 463342, "is_parallel": true, "self": 56.55792227307279 } } } } } } } } } } }, "trainer_advance": { "total": 540.9208067160394, "count": 231672, "self": 7.22177492094454, "children": { "process_trajectory": { "total": 164.285700441093, "count": 231672, "self": 162.88978879709407, "children": { "RLTrainer._checkpoint": { "total": 1.395911643998943, "count": 10, "self": 1.395911643998943 } } }, "_update_policy": { "total": 369.4133313540018, "count": 97, "self": 309.80879755399576, "children": { "TorchPPOOptimizer.update": { "total": 59.60453380000604, "count": 2910, "self": 59.60453380000604 } } } } } } }, "trainer_threads": { "total": 9.240002327715047e-07, "count": 1, "self": 9.240002327715047e-07 }, "TrainerController._save_models": { "total": 0.11724317300013354, "count": 1, "self": 0.0021288030002324376, "children": { "RLTrainer._checkpoint": { "total": 0.1151143699999011, "count": 1, "self": 0.1151143699999011 } } } } } } }