{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 0.8939313292503357, "min": 0.8939313292503357, "max": 1.4150216579437256, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 44802.9453125, "min": 43728.9609375, "max": 78281.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 109.58980044345898, "min": 102.01646090534979, "max": 364.59124087591243, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49425.0, "min": 49061.0, "max": 50074.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999689.0, "min": 49937.0, "max": 1999689.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999689.0, "min": 49937.0, "max": 1999689.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.203591823577881, "min": -0.06476376205682755, "max": 2.2221322059631348, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 993.8199462890625, "min": -9.520273208618164, "max": 1064.7984619140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.651096051918165, "min": 1.8489283619283818, "max": 3.955617983905456, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1646.6443194150925, "min": 271.79246920347214, "max": 1844.2182909846306, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.651096051918165, "min": 1.8489283619283818, "max": 3.955617983905456, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1646.6443194150925, "min": 271.79246920347214, "max": 1844.2182909846306, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016847250777290254, "min": 0.016126701320172288, "max": 0.024698878979931276, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05054175233187076, "min": 0.032253402640344576, "max": 0.06979979390550094, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.03354456250866254, "min": 0.020223973070581755, "max": 0.3462303774741789, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10063368752598763, "min": 0.041226028961439926, "max": 0.6924607549483578, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.212609892913332e-05, "min": 3.212609892913332e-05, "max": 0.002952891001570301, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.637829678739997e-05, "min": 9.637829678739997e-05, "max": 0.00843701851876605, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107086666666665, "min": 0.10107086666666665, "max": 0.19842970000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30321259999999994, "min": 0.20727660000000003, "max": 0.58123395, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.343624666666665e-05, "min": 6.343624666666665e-05, "max": 0.004921642029999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019030873999999995, "min": 0.00019030873999999995, "max": 0.014063574105000002, "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": "1739420716", "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=Huggylr0.003 --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": "1739423120" }, "total": 2404.4697699609997, "count": 1, "self": 0.42525567799930286, "children": { "run_training.setup": { "total": 0.020753582999986975, "count": 1, "self": 0.020753582999986975 }, "TrainerController.start_learning": { "total": 2404.0237607000004, "count": 1, "self": 4.353786434383892, "children": { "TrainerController._reset_env": { "total": 2.073985814000025, "count": 1, "self": 2.073985814000025 }, "TrainerController.advance": { "total": 2397.472431847617, "count": 230221, "self": 4.41543324240638, "children": { "env_step": { "total": 1919.5685225152056, "count": 230221, "self": 1499.2046224381806, "children": { "SubprocessEnvManager._take_step": { "total": 417.8092273679458, "count": 230221, "self": 15.123129654817603, "children": { "TorchPolicy.evaluate": { "total": 402.6860977131282, "count": 222911, "self": 402.6860977131282 } } }, "workers": { "total": 2.5546727090791137, "count": 230221, "self": 0.0, "children": { "worker_root": { "total": 2396.819087406405, "count": 230221, "is_parallel": true, "self": 1171.1851623262319, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008997900004032999, "count": 1, "is_parallel": true, "self": 0.00022793300013290718, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006718570002703927, "count": 2, "is_parallel": true, "self": 0.0006718570002703927 } } }, "UnityEnvironment.step": { "total": 0.029245393000110198, "count": 1, "is_parallel": true, "self": 0.0002624450003168022, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020609500006685266, "count": 1, "is_parallel": true, "self": 0.00020609500006685266 }, "communicator.exchange": { "total": 0.027966925999862724, "count": 1, "is_parallel": true, "self": 0.027966925999862724 }, "steps_from_proto": { "total": 0.0008099269998638192, "count": 1, "is_parallel": true, "self": 0.0001885729993773566, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006213540004864626, "count": 2, "is_parallel": true, "self": 0.0006213540004864626 } } } } } } }, "UnityEnvironment.step": { "total": 1225.633925080173, "count": 230220, "is_parallel": true, "self": 36.216801928896984, "children": { "UnityEnvironment._generate_step_input": { "total": 80.55140950094165, "count": 230220, "is_parallel": true, "self": 80.55140950094165 }, "communicator.exchange": { "total": 1023.7091733762063, "count": 230220, "is_parallel": true, "self": 1023.7091733762063 }, "steps_from_proto": { "total": 85.15654027412802, "count": 230220, "is_parallel": true, "self": 29.747219577590386, "children": { "_process_rank_one_or_two_observation": { "total": 55.409320696537634, "count": 460440, "is_parallel": true, "self": 55.409320696537634 } } } } } } } } } } }, "trainer_advance": { "total": 473.48847609000495, "count": 230221, "self": 6.174284807926597, "children": { "process_trajectory": { "total": 144.4067112840794, "count": 230221, "self": 143.05759648408002, "children": { "RLTrainer._checkpoint": { "total": 1.34911479999937, "count": 10, "self": 1.34911479999937 } } }, "_update_policy": { "total": 322.90747999799896, "count": 97, "self": 258.2100226640009, "children": { "TorchPPOOptimizer.update": { "total": 64.69745733399805, "count": 2910, "self": 64.69745733399805 } } } } } } }, "trainer_threads": { "total": 9.049999789567664e-07, "count": 1, "self": 9.049999789567664e-07 }, "TrainerController._save_models": { "total": 0.12355569899955299, "count": 1, "self": 0.0021042899998064968, "children": { "RLTrainer._checkpoint": { "total": 0.12145140899974649, "count": 1, "self": 0.12145140899974649 } } } } } } }