{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.407737135887146, "min": 1.407737135887146, "max": 1.4283111095428467, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71475.0390625, "min": 69567.625, "max": 76670.21875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.62323943661971, "min": 75.46788990825688, "max": 394.755905511811, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49202.0, "min": 48942.0, "max": 50153.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999945.0, "min": 49545.0, "max": 1999945.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999945.0, "min": 49545.0, "max": 1999945.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4941837787628174, "min": 0.08929670602083206, "max": 2.5023579597473145, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1416.6964111328125, "min": 11.251384735107422, "max": 1618.9415283203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.867357066924303, "min": 1.775967292960674, "max": 4.051920339561278, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2196.6588140130043, "min": 223.77187891304493, "max": 2527.5081028342247, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.867357066924303, "min": 1.775967292960674, "max": 4.051920339561278, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2196.6588140130043, "min": 223.77187891304493, "max": 2527.5081028342247, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017274779772318043, "min": 0.01404156981850267, "max": 0.020442034504473364, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051824339316954134, "min": 0.028143292541305223, "max": 0.05664533710029597, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04885669015347958, "min": 0.02034824586783846, "max": 0.0634689266482989, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14657007046043874, "min": 0.04069649173567692, "max": 0.18914192902545135, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8076987308000004e-06, "min": 3.8076987308000004e-06, "max": 0.0002953704015432, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1423096192400002e-05, "min": 1.1423096192400002e-05, "max": 0.0008438301187232999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126920000000002, "min": 0.10126920000000002, "max": 0.19845680000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30380760000000007, "min": 0.20767205000000005, "max": 0.5812767, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.333308000000003e-05, "min": 7.333308000000003e-05, "max": 0.004922994320000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002199992400000001, "min": 0.0002199992400000001, "max": 0.014065707330000003, "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": "1673507702", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1673509924" }, "total": 2222.627279431, "count": 1, "self": 0.40044932599994354, "children": { "run_training.setup": { "total": 0.10836598599962599, "count": 1, "self": 0.10836598599962599 }, "TrainerController.start_learning": { "total": 2222.1184641190002, "count": 1, "self": 3.8752618601074573, "children": { "TrainerController._reset_env": { "total": 8.89318898900001, "count": 1, "self": 8.89318898900001 }, "TrainerController.advance": { "total": 2209.239492424893, "count": 233144, "self": 4.040084092038342, "children": { "env_step": { "total": 1743.1198361158258, "count": 233144, "self": 1460.388395498423, "children": { "SubprocessEnvManager._take_step": { "total": 280.13124156619233, "count": 233144, "self": 14.405490250146613, "children": { "TorchPolicy.evaluate": { "total": 265.7257513160457, "count": 223068, "self": 65.67057021317123, "children": { "TorchPolicy.sample_actions": { "total": 200.05518110287449, "count": 223068, "self": 200.05518110287449 } } } } }, "workers": { "total": 2.6001990512104385, "count": 233144, "self": 0.0, "children": { "worker_root": { "total": 2214.085864111855, "count": 233144, "is_parallel": true, "self": 1017.4238119805605, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002046966000307293, "count": 1, "is_parallel": true, "self": 0.00029127500056347344, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017556909997438197, "count": 2, "is_parallel": true, "self": 0.0017556909997438197 } } }, "UnityEnvironment.step": { "total": 0.029703636000704137, "count": 1, "is_parallel": true, "self": 0.0002774230015347712, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022655799966742052, "count": 1, "is_parallel": true, "self": 0.00022655799966742052 }, "communicator.exchange": { "total": 0.028259757999876456, "count": 1, "is_parallel": true, "self": 0.028259757999876456 }, "steps_from_proto": { "total": 0.0009398969996254891, "count": 1, "is_parallel": true, "self": 0.0004271789994163555, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005127180002091336, "count": 2, "is_parallel": true, "self": 0.0005127180002091336 } } } } } } }, "UnityEnvironment.step": { "total": 1196.6620521312943, "count": 233143, "is_parallel": true, "self": 34.0133164375593, "children": { "UnityEnvironment._generate_step_input": { "total": 77.39001766980073, "count": 233143, "is_parallel": true, "self": 77.39001766980073 }, "communicator.exchange": { "total": 988.8165375190329, "count": 233143, "is_parallel": true, "self": 988.8165375190329 }, "steps_from_proto": { "total": 96.44218050490144, "count": 233143, "is_parallel": true, "self": 42.30157201637212, "children": { "_process_rank_one_or_two_observation": { "total": 54.140608488529324, "count": 466286, "is_parallel": true, "self": 54.140608488529324 } } } } } } } } } } }, "trainer_advance": { "total": 462.0795722170287, "count": 233144, "self": 5.807121670744891, "children": { "process_trajectory": { "total": 147.85930028327584, "count": 233144, "self": 146.69630041627715, "children": { "RLTrainer._checkpoint": { "total": 1.162999866998689, "count": 10, "self": 1.162999866998689 } } }, "_update_policy": { "total": 308.413150263008, "count": 97, "self": 255.5242802840021, "children": { "TorchPPOOptimizer.update": { "total": 52.888869979005904, "count": 2910, "self": 52.888869979005904 } } } } } } }, "trainer_threads": { "total": 8.299994078697637e-07, "count": 1, "self": 8.299994078697637e-07 }, "TrainerController._save_models": { "total": 0.11052001500047481, "count": 1, "self": 0.001972339000531065, "children": { "RLTrainer._checkpoint": { "total": 0.10854767599994375, "count": 1, "self": 0.10854767599994375 } } } } } } }