{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4060702323913574, "min": 1.4060702323913574, "max": 1.425771713256836, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69376.9140625, "min": 68146.296875, "max": 78316.09375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 108.77412280701755, "min": 90.67032967032966, "max": 397.76984126984127, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49601.0, "min": 48829.0, "max": 50238.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49496.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49496.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3516082763671875, "min": 0.11942727118730545, "max": 2.4171111583709717, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1072.3333740234375, "min": 14.9284086227417, "max": 1297.953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7086700157899606, "min": 1.7839767813682557, "max": 3.868096522937979, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1691.153527200222, "min": 222.99709767103195, "max": 1990.1310638189316, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7086700157899606, "min": 1.7839767813682557, "max": 3.868096522937979, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1691.153527200222, "min": 222.99709767103195, "max": 1990.1310638189316, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01421884174827331, "min": 0.013554000713823674, "max": 0.020701688322393844, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.02843768349654662, "min": 0.027108001427647348, "max": 0.055526733071504464, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04550764045367638, "min": 0.021207911428064108, "max": 0.06238686845948299, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09101528090735277, "min": 0.042415822856128216, "max": 0.18206091448664666, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.356923547725008e-06, "min": 4.356923547725008e-06, "max": 0.00029530260156580005, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.713847095450016e-06, "min": 8.713847095450016e-06, "max": 0.0008438673187109001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10145227500000001, "min": 0.10145227500000001, "max": 0.1984342, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20290455000000002, "min": 0.20290455000000002, "max": 0.5812891000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.246852250000017e-05, "min": 8.246852250000017e-05, "max": 0.004921866580000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016493704500000035, "min": 0.00016493704500000035, "max": 0.01406632609, "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": "1741034042", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741036499" }, "total": 2457.582379874, "count": 1, "self": 0.44064508099972954, "children": { "run_training.setup": { "total": 0.02353298100001666, "count": 1, "self": 0.02353298100001666 }, "TrainerController.start_learning": { "total": 2457.118201812, "count": 1, "self": 4.3048802360262926, "children": { "TrainerController._reset_env": { "total": 2.9007841080001526, "count": 1, "self": 2.9007841080001526 }, "TrainerController.advance": { "total": 2449.7984821519726, "count": 231849, "self": 4.4866709780994825, "children": { "env_step": { "total": 1963.32288618101, "count": 231849, "self": 1538.7467929639704, "children": { "SubprocessEnvManager._take_step": { "total": 421.84801585009154, "count": 231849, "self": 15.846931305068892, "children": { "TorchPolicy.evaluate": { "total": 406.00108454502265, "count": 222898, "self": 406.00108454502265 } } }, "workers": { "total": 2.7280773669481277, "count": 231849, "self": 0.0, "children": { "worker_root": { "total": 2449.835093817889, "count": 231849, "is_parallel": true, "self": 1195.2303842877895, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010548119998929906, "count": 1, "is_parallel": true, "self": 0.000382080999770551, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006727310001224396, "count": 2, "is_parallel": true, "self": 0.0006727310001224396 } } }, "UnityEnvironment.step": { "total": 0.029892999000139753, "count": 1, "is_parallel": true, "self": 0.0003123430001323868, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018569300004855904, "count": 1, "is_parallel": true, "self": 0.00018569300004855904 }, "communicator.exchange": { "total": 0.028682144999947923, "count": 1, "is_parallel": true, "self": 0.028682144999947923 }, "steps_from_proto": { "total": 0.0007128180000108841, "count": 1, "is_parallel": true, "self": 0.00021095100009915768, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005018669999117265, "count": 2, "is_parallel": true, "self": 0.0005018669999117265 } } } } } } }, "UnityEnvironment.step": { "total": 1254.6047095300996, "count": 231848, "is_parallel": true, "self": 37.0876381141959, "children": { "UnityEnvironment._generate_step_input": { "total": 82.77212406094486, "count": 231848, "is_parallel": true, "self": 82.77212406094486 }, "communicator.exchange": { "total": 1046.780344145072, "count": 231848, "is_parallel": true, "self": 1046.780344145072 }, "steps_from_proto": { "total": 87.96460320988695, "count": 231848, "is_parallel": true, "self": 32.70861808384643, "children": { "_process_rank_one_or_two_observation": { "total": 55.255985126040514, "count": 463696, "is_parallel": true, "self": 55.255985126040514 } } } } } } } } } } }, "trainer_advance": { "total": 481.9889249928631, "count": 231849, "self": 6.436400537764484, "children": { "process_trajectory": { "total": 160.53936451410163, "count": 231849, "self": 159.2975108431017, "children": { "RLTrainer._checkpoint": { "total": 1.2418536709999444, "count": 10, "self": 1.2418536709999444 } } }, "_update_policy": { "total": 315.01315994099696, "count": 96, "self": 251.40059765500928, "children": { "TorchPPOOptimizer.update": { "total": 63.61256228598768, "count": 2880, "self": 63.61256228598768 } } } } } } }, "trainer_threads": { "total": 8.71000338520389e-07, "count": 1, "self": 8.71000338520389e-07 }, "TrainerController._save_models": { "total": 0.11405444500041995, "count": 1, "self": 0.0018243510003230767, "children": { "RLTrainer._checkpoint": { "total": 0.11223009400009687, "count": 1, "self": 0.11223009400009687 } } } } } } }