{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405005693435669, "min": 1.405005693435669, "max": 1.4285550117492676, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69383.3984375, "min": 68519.7265625, "max": 77599.3359375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.30834752981261, "min": 79.36757624398074, "max": 408.88524590163934, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49489.0, "min": 48894.0, "max": 50219.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999992.0, "min": 49256.0, "max": 1999992.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999992.0, "min": 49256.0, "max": 1999992.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4125852584838867, "min": 0.11043550819158554, "max": 2.4685142040252686, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1416.1875, "min": 13.362696647644043, "max": 1509.2978515625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8025827413929383, "min": 1.883230386686719, "max": 3.9408626591583484, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2232.1160691976547, "min": 227.87087678909302, "max": 2362.513219833374, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8025827413929383, "min": 1.883230386686719, "max": 3.9408626591583484, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2232.1160691976547, "min": 227.87087678909302, "max": 2362.513219833374, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018192213591424256, "min": 0.013567476241910804, "max": 0.02119191470555961, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05457664077427277, "min": 0.029447538523042265, "max": 0.05457664077427277, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05690570146673255, "min": 0.021562012409170467, "max": 0.05948861992607514, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17071710440019766, "min": 0.043124024818340934, "max": 0.17696272681156794, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3404488865500025e-06, "min": 3.3404488865500025e-06, "max": 0.00029529907656697493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0021346659650007e-05, "min": 1.0021346659650007e-05, "max": 0.0008439267186910998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111344999999998, "min": 0.10111344999999998, "max": 0.19843302499999999, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033403499999999, "min": 0.207416, "max": 0.5813089, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.556115500000005e-05, "min": 6.556115500000005e-05, "max": 0.0049218079475, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019668346500000016, "min": 0.00019668346500000016, "max": 0.01406731411, "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": "1684241279", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684243678" }, "total": 2399.228787819, "count": 1, "self": 0.4432486829996378, "children": { "run_training.setup": { "total": 0.04184711300001709, "count": 1, "self": 0.04184711300001709 }, "TrainerController.start_learning": { "total": 2398.743692023, "count": 1, "self": 4.225083478983834, "children": { "TrainerController._reset_env": { "total": 3.9114857430000143, "count": 1, "self": 3.9114857430000143 }, "TrainerController.advance": { "total": 2390.479337364016, "count": 232229, "self": 4.3214789440926324, "children": { "env_step": { "total": 1854.610519245065, "count": 232229, "self": 1566.978278850997, "children": { "SubprocessEnvManager._take_step": { "total": 284.83962827306704, "count": 232229, "self": 16.493883429985715, "children": { "TorchPolicy.evaluate": { "total": 268.3457448430813, "count": 222853, "self": 268.3457448430813 } } }, "workers": { "total": 2.7926121210011274, "count": 232229, "self": 0.0, "children": { "worker_root": { "total": 2391.132236410976, "count": 232229, "is_parallel": true, "self": 1108.6879774350261, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008592479999833813, "count": 1, "is_parallel": true, "self": 0.00024283999999852313, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006164079999848582, "count": 2, "is_parallel": true, "self": 0.0006164079999848582 } } }, "UnityEnvironment.step": { "total": 0.027894659000025968, "count": 1, "is_parallel": true, "self": 0.00036338200010277433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023195599999326078, "count": 1, "is_parallel": true, "self": 0.00023195599999326078 }, "communicator.exchange": { "total": 0.02660110899995516, "count": 1, "is_parallel": true, "self": 0.02660110899995516 }, "steps_from_proto": { "total": 0.0006982119999747738, "count": 1, "is_parallel": true, "self": 0.0002091859999495682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004890260000252056, "count": 2, "is_parallel": true, "self": 0.0004890260000252056 } } } } } } }, "UnityEnvironment.step": { "total": 1282.4442589759499, "count": 232228, "is_parallel": true, "self": 38.749054095837664, "children": { "UnityEnvironment._generate_step_input": { "total": 78.15499972301518, "count": 232228, "is_parallel": true, "self": 78.15499972301518 }, "communicator.exchange": { "total": 1072.351425440057, "count": 232228, "is_parallel": true, "self": 1072.351425440057 }, "steps_from_proto": { "total": 93.18877971703989, "count": 232228, "is_parallel": true, "self": 34.27108493301648, "children": { "_process_rank_one_or_two_observation": { "total": 58.91769478402341, "count": 464456, "is_parallel": true, "self": 58.91769478402341 } } } } } } } } } } }, "trainer_advance": { "total": 531.547339174858, "count": 232229, "self": 6.569917325772849, "children": { "process_trajectory": { "total": 136.01581854208666, "count": 232229, "self": 134.68493181408667, "children": { "RLTrainer._checkpoint": { "total": 1.3308867279999959, "count": 10, "self": 1.3308867279999959 } } }, "_update_policy": { "total": 388.96160330699854, "count": 97, "self": 328.3198832400134, "children": { "TorchPPOOptimizer.update": { "total": 60.64172006698516, "count": 2910, "self": 60.64172006698516 } } } } } } }, "trainer_threads": { "total": 1.4720003491675016e-06, "count": 1, "self": 1.4720003491675016e-06 }, "TrainerController._save_models": { "total": 0.12778396500016242, "count": 1, "self": 0.0020505150005192263, "children": { "RLTrainer._checkpoint": { "total": 0.1257334499996432, "count": 1, "self": 0.1257334499996432 } } } } } } }