{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.409009337425232, "min": 1.4089884757995605, "max": 1.430418848991394, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69961.5390625, "min": 68684.234375, "max": 78056.9375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 74.55287009063444, "min": 72.3108504398827, "max": 397.2857142857143, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49354.0, "min": 49247.0, "max": 50058.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999956.0, "min": 49861.0, "max": 1999956.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999956.0, "min": 49861.0, "max": 1999956.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4647295475006104, "min": 0.013108772225677967, "max": 2.5507652759552, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1631.6510009765625, "min": 1.638596534729004, "max": 1689.0230712890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.831091271246308, "min": 1.8512081763744355, "max": 4.090535478753255, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2536.182421565056, "min": 231.40102204680443, "max": 2720.2060933709145, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.831091271246308, "min": 1.8512081763744355, "max": 4.090535478753255, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2536.182421565056, "min": 231.40102204680443, "max": 2720.2060933709145, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017417761943397638, "min": 0.013617092173937332, "max": 0.020379835398246844, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05225328583019291, "min": 0.027234184347874665, "max": 0.05915522924721396, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05834953366882271, "min": 0.02364491798604528, "max": 0.060949309749735725, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17504860100646813, "min": 0.04728983597209056, "max": 0.18284792924920718, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.827748724116672e-06, "min": 3.827748724116672e-06, "max": 0.000295372426542525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1483246172350015e-05, "min": 1.1483246172350015e-05, "max": 0.0008441748186083999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127588333333333, "min": 0.10127588333333333, "max": 0.19845747499999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30382765, "min": 0.20769879999999996, "max": 0.5813916, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.366657833333341e-05, "min": 7.366657833333341e-05, "max": 0.0049230280025, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022099973500000022, "min": 0.00022099973500000022, "max": 0.014071440840000003, "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": "1715610605", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715613150" }, "total": 2545.053106271, "count": 1, "self": 0.8333925830002045, "children": { "run_training.setup": { "total": 0.054971101999854, "count": 1, "self": 0.054971101999854 }, "TrainerController.start_learning": { "total": 2544.164742586, "count": 1, "self": 4.674756167016312, "children": { "TrainerController._reset_env": { "total": 2.808281827999963, "count": 1, "self": 2.808281827999963 }, "TrainerController.advance": { "total": 2536.5012725259835, "count": 233511, "self": 4.887343994960247, "children": { "env_step": { "total": 2012.9746376349003, "count": 233511, "self": 1665.5104392429237, "children": { "SubprocessEnvManager._take_step": { "total": 344.3580354720202, "count": 233511, "self": 17.437015884180255, "children": { "TorchPolicy.evaluate": { "total": 326.92101958783996, "count": 222959, "self": 326.92101958783996 } } }, "workers": { "total": 3.1061629199564322, "count": 233511, "self": 0.0, "children": { "worker_root": { "total": 2536.4249568870846, "count": 233511, "is_parallel": true, "self": 1197.0008590620996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00092997199999445, "count": 1, "is_parallel": true, "self": 0.0002420449998226104, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006879270001718396, "count": 2, "is_parallel": true, "self": 0.0006879270001718396 } } }, "UnityEnvironment.step": { "total": 0.031117494999989503, "count": 1, "is_parallel": true, "self": 0.0003816040000401699, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021663799998350441, "count": 1, "is_parallel": true, "self": 0.00021663799998350441 }, "communicator.exchange": { "total": 0.02977392899992992, "count": 1, "is_parallel": true, "self": 0.02977392899992992 }, "steps_from_proto": { "total": 0.0007453240000359074, "count": 1, "is_parallel": true, "self": 0.00020359300015115878, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005417309998847486, "count": 2, "is_parallel": true, "self": 0.0005417309998847486 } } } } } } }, "UnityEnvironment.step": { "total": 1339.424097824985, "count": 233510, "is_parallel": true, "self": 40.36704040384552, "children": { "UnityEnvironment._generate_step_input": { "total": 87.44293742807758, "count": 233510, "is_parallel": true, "self": 87.44293742807758 }, "communicator.exchange": { "total": 1116.4714705020058, "count": 233510, "is_parallel": true, "self": 1116.4714705020058 }, "steps_from_proto": { "total": 95.14264949105609, "count": 233510, "is_parallel": true, "self": 36.37826686489484, "children": { "_process_rank_one_or_two_observation": { "total": 58.76438262616125, "count": 467020, "is_parallel": true, "self": 58.76438262616125 } } } } } } } } } } }, "trainer_advance": { "total": 518.6392908961229, "count": 233511, "self": 6.648581821124026, "children": { "process_trajectory": { "total": 170.95879198099874, "count": 233511, "self": 169.595193878999, "children": { "RLTrainer._checkpoint": { "total": 1.3635981019997416, "count": 10, "self": 1.3635981019997416 } } }, "_update_policy": { "total": 341.03191709400016, "count": 97, "self": 276.1720249379948, "children": { "TorchPPOOptimizer.update": { "total": 64.85989215600534, "count": 2910, "self": 64.85989215600534 } } } } } } }, "trainer_threads": { "total": 1.7209999896294903e-06, "count": 1, "self": 1.7209999896294903e-06 }, "TrainerController._save_models": { "total": 0.1804303440003423, "count": 1, "self": 0.0030349250000654138, "children": { "RLTrainer._checkpoint": { "total": 0.1773954190002769, "count": 1, "self": 0.1773954190002769 } } } } } } }