{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4101938009262085, "min": 1.4101938009262085, "max": 1.4303182363510132, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72137.0546875, "min": 67556.8125, "max": 77680.53125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 100.38571428571429, "min": 87.00880281690141, "max": 422.6386554621849, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49189.0, "min": 48994.0, "max": 50294.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999986.0, "min": 49861.0, "max": 1999986.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999986.0, "min": 49861.0, "max": 1999986.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3266077041625977, "min": 0.09293240308761597, "max": 2.408137321472168, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1140.0377197265625, "min": 10.966023445129395, "max": 1300.1552734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5776075110143544, "min": 2.0825654621851646, "max": 3.910012868947761, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1753.0276803970337, "min": 245.74272453784943, "max": 2125.7759407162666, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5776075110143544, "min": 2.0825654621851646, "max": 3.910012868947761, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1753.0276803970337, "min": 245.74272453784943, "max": 2125.7759407162666, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016160495659601617, "min": 0.014036164216910643, "max": 0.019853399661951696, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04848148697880485, "min": 0.028072328433821285, "max": 0.05882054300066859, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.050253532412979335, "min": 0.022303750428060688, "max": 0.05668431222438812, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.150760597238938, "min": 0.044607500856121376, "max": 0.16457236868639785, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.437098854333335e-06, "min": 3.437098854333335e-06, "max": 0.0002953668015444, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0311296563000004e-05, "min": 1.0311296563000004e-05, "max": 0.0008444790185069999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114566666666665, "min": 0.10114566666666665, "max": 0.19845559999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30343699999999996, "min": 0.2074737, "max": 0.5814930000000003, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.71687666666667e-05, "min": 6.71687666666667e-05, "max": 0.0049229344399999994, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020150630000000008, "min": 0.00020150630000000008, "max": 0.014076500700000001, "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": "1711410041", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/joeny/.local/bin/mlagents-learn ./ml-agents/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": "1711411543" }, "total": 1501.4609704649997, "count": 1, "self": 0.2686430799999471, "children": { "run_training.setup": { "total": 0.05590519699990182, "count": 1, "self": 0.05590519699990182 }, "TrainerController.start_learning": { "total": 1501.1364221879999, "count": 1, "self": 3.8536674539923297, "children": { "TrainerController._reset_env": { "total": 2.640385961999982, "count": 1, "self": 2.640385961999982 }, "TrainerController.advance": { "total": 1494.4981685010075, "count": 231864, "self": 3.956553463864111, "children": { "env_step": { "total": 1194.0748922501075, "count": 231864, "self": 931.1358908081634, "children": { "SubprocessEnvManager._take_step": { "total": 260.18084366413996, "count": 231864, "self": 11.398022897238661, "children": { "TorchPolicy.evaluate": { "total": 248.7828207669013, "count": 223048, "self": 248.7828207669013 } } }, "workers": { "total": 2.758157777804172, "count": 231864, "self": 0.0, "children": { "worker_root": { "total": 1496.4045831399872, "count": 231864, "is_parallel": true, "self": 767.3394043059857, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00043524600005184766, "count": 1, "is_parallel": true, "self": 0.00011404899987610406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003211970001757436, "count": 2, "is_parallel": true, "self": 0.0003211970001757436 } } }, "UnityEnvironment.step": { "total": 0.01420379099999991, "count": 1, "is_parallel": true, "self": 0.000259383999491547, "children": { "UnityEnvironment._generate_step_input": { "total": 9.913200028677238e-05, "count": 1, "is_parallel": true, "self": 9.913200028677238e-05 }, "communicator.exchange": { "total": 0.013185758999952668, "count": 1, "is_parallel": true, "self": 0.013185758999952668 }, "steps_from_proto": { "total": 0.0006595160002689227, "count": 1, "is_parallel": true, "self": 0.00014381800019691582, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005156980000720068, "count": 2, "is_parallel": true, "self": 0.0005156980000720068 } } } } } } }, "UnityEnvironment.step": { "total": 729.0651788340015, "count": 231863, "is_parallel": true, "self": 28.658331190848003, "children": { "UnityEnvironment._generate_step_input": { "total": 45.104008083017106, "count": 231863, "is_parallel": true, "self": 45.104008083017106 }, "communicator.exchange": { "total": 590.8766309081011, "count": 231863, "is_parallel": true, "self": 590.8766309081011 }, "steps_from_proto": { "total": 64.42620865203526, "count": 231863, "is_parallel": true, "self": 21.12359193990096, "children": { "_process_rank_one_or_two_observation": { "total": 43.302616712134295, "count": 463726, "is_parallel": true, "self": 43.302616712134295 } } } } } } } } } } }, "trainer_advance": { "total": 296.4667227870359, "count": 231864, "self": 5.404601170814658, "children": { "process_trajectory": { "total": 101.33848838022232, "count": 231864, "self": 99.76693791222215, "children": { "RLTrainer._checkpoint": { "total": 1.5715504680001686, "count": 10, "self": 1.5715504680001686 } } }, "_update_policy": { "total": 189.72363323599893, "count": 97, "self": 152.63800274199411, "children": { "TorchPPOOptimizer.update": { "total": 37.08563049400482, "count": 2910, "self": 37.08563049400482 } } } } } } }, "trainer_threads": { "total": 6.130003384896554e-07, "count": 1, "self": 6.130003384896554e-07 }, "TrainerController._save_models": { "total": 0.1441996579997067, "count": 1, "self": 0.0014341369997055153, "children": { "RLTrainer._checkpoint": { "total": 0.14276552100000117, "count": 1, "self": 0.14276552100000117 } } } } } } }