{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4040826559066772, "min": 1.4040826559066772, "max": 1.4278944730758667, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69650.921875, "min": 68412.5078125, "max": 77878.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 122.43703703703704, "min": 102.11387163561076, "max": 390.0387596899225, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49587.0, "min": 48958.0, "max": 50315.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999993.0, "min": 49695.0, "max": 1999993.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999993.0, "min": 49695.0, "max": 1999993.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.196301221847534, "min": 0.026159998029470444, "max": 2.3311574459075928, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 889.501953125, "min": 3.348479747772217, "max": 1125.7044677734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4863408185817577, "min": 1.8076969583053142, "max": 3.7915526054006943, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1411.9680315256119, "min": 231.38521066308022, "max": 1789.7524199485779, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4863408185817577, "min": 1.8076969583053142, "max": 3.7915526054006943, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1411.9680315256119, "min": 231.38521066308022, "max": 1789.7524199485779, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015750501074702092, "min": 0.013204676759293458, "max": 0.020297174263881362, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.031501002149404184, "min": 0.026409353518586916, "max": 0.056660141151708865, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04032895208025972, "min": 0.022484416204194228, "max": 0.06144029576745299, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08065790416051943, "min": 0.044968832408388455, "max": 0.18432088730235896, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.368698543800005e-06, "min": 4.368698543800005e-06, "max": 0.00029527785157405003, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.73739708760001e-06, "min": 8.73739708760001e-06, "max": 0.0008438632687122498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10145619999999997, "min": 0.10145619999999997, "max": 0.19842595000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20291239999999994, "min": 0.20291239999999994, "max": 0.58128775, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.266438000000007e-05, "min": 8.266438000000007e-05, "max": 0.004921454905000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016532876000000015, "min": 0.00016532876000000015, "max": 0.014066258725, "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": "1676885850", "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": "1676888521" }, "total": 2670.511189289, "count": 1, "self": 0.8445179620002818, "children": { "run_training.setup": { "total": 0.1847372690000384, "count": 1, "self": 0.1847372690000384 }, "TrainerController.start_learning": { "total": 2669.4819340579998, "count": 1, "self": 5.048161579071802, "children": { "TrainerController._reset_env": { "total": 10.927719146000072, "count": 1, "self": 10.927719146000072 }, "TrainerController.advance": { "total": 2653.3018924109274, "count": 230774, "self": 5.314520238661316, "children": { "env_step": { "total": 2102.7815659481107, "count": 230774, "self": 1750.8270917351115, "children": { "SubprocessEnvManager._take_step": { "total": 348.72163596803193, "count": 230774, "self": 17.790076807023183, "children": { "TorchPolicy.evaluate": { "total": 330.93155916100875, "count": 222964, "self": 81.69807415889329, "children": { "TorchPolicy.sample_actions": { "total": 249.23348500211546, "count": 222964, "self": 249.23348500211546 } } } } }, "workers": { "total": 3.232838244967411, "count": 230774, "self": 0.0, "children": { "worker_root": { "total": 2659.656498803114, "count": 230774, "is_parallel": true, "self": 1241.5202409381827, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020190369999681934, "count": 1, "is_parallel": true, "self": 0.0004727120000325158, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015463249999356776, "count": 2, "is_parallel": true, "self": 0.0015463249999356776 } } }, "UnityEnvironment.step": { "total": 0.031174063999969803, "count": 1, "is_parallel": true, "self": 0.00032207100014147727, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020732899997710774, "count": 1, "is_parallel": true, "self": 0.00020732899997710774 }, "communicator.exchange": { "total": 0.029590132999942398, "count": 1, "is_parallel": true, "self": 0.029590132999942398 }, "steps_from_proto": { "total": 0.0010545309999088204, "count": 1, "is_parallel": true, "self": 0.0005087119999416245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005458189999671959, "count": 2, "is_parallel": true, "self": 0.0005458189999671959 } } } } } } }, "UnityEnvironment.step": { "total": 1418.1362578649314, "count": 230773, "is_parallel": true, "self": 41.90165329297315, "children": { "UnityEnvironment._generate_step_input": { "total": 91.08801278009605, "count": 230773, "is_parallel": true, "self": 91.08801278009605 }, "communicator.exchange": { "total": 1181.2134370368972, "count": 230773, "is_parallel": true, "self": 1181.2134370368972 }, "steps_from_proto": { "total": 103.93315475496513, "count": 230773, "is_parallel": true, "self": 44.548842616932575, "children": { "_process_rank_one_or_two_observation": { "total": 59.384312138032556, "count": 461546, "is_parallel": true, "self": 59.384312138032556 } } } } } } } } } } }, "trainer_advance": { "total": 545.2058062241553, "count": 230774, "self": 8.224842512216924, "children": { "process_trajectory": { "total": 175.8152191739398, "count": 230774, "self": 174.4596408329396, "children": { "RLTrainer._checkpoint": { "total": 1.3555783410001823, "count": 10, "self": 1.3555783410001823 } } }, "_update_policy": { "total": 361.16574453799853, "count": 96, "self": 303.0982876540089, "children": { "TorchPPOOptimizer.update": { "total": 58.06745688398962, "count": 2880, "self": 58.06745688398962 } } } } } } }, "trainer_threads": { "total": 1.452000105928164e-06, "count": 1, "self": 1.452000105928164e-06 }, "TrainerController._save_models": { "total": 0.20415947000037704, "count": 1, "self": 0.0029570320002676453, "children": { "RLTrainer._checkpoint": { "total": 0.2012024380001094, "count": 1, "self": 0.2012024380001094 } } } } } } }