{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4081580638885498, "min": 1.4081580638885498, "max": 1.4299359321594238, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 67739.4453125, "min": 67739.4453125, "max": 77998.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 100.86326530612244, "min": 70.32810271041369, "max": 396.56692913385825, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49423.0, "min": 48826.0, "max": 50364.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999936.0, "min": 49741.0, "max": 1999936.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999936.0, "min": 49741.0, "max": 1999936.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3723652362823486, "min": -0.09381920099258423, "max": 2.522627592086792, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1164.831298828125, "min": -11.821219444274902, "max": 1746.667236328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4971060803854295, "min": 1.8632938334393123, "max": 4.000147507945002, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1717.079085469246, "min": 234.77502301335335, "max": 2774.223048388958, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4971060803854295, "min": 1.8632938334393123, "max": 4.000147507945002, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1717.079085469246, "min": 234.77502301335335, "max": 2774.223048388958, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.013962742061832817, "min": 0.013962742061832817, "max": 0.01997995570030374, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04188822618549845, "min": 0.028504544915631414, "max": 0.056037559693618275, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04967296462919977, "min": 0.023114980043222506, "max": 0.062390311559041345, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1490188938875993, "min": 0.04622996008644501, "max": 0.18717093467712403, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.788198737299993e-06, "min": 3.788198737299993e-06, "max": 0.00029533282655572494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.136459621189998e-05, "min": 1.136459621189998e-05, "max": 0.0008441059686313498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126269999999998, "min": 0.10126269999999998, "max": 0.198444275, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30378809999999995, "min": 0.20765625000000004, "max": 0.5813686500000003, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.300872999999995e-05, "min": 7.300872999999995e-05, "max": 0.0049223693225, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021902618999999982, "min": 0.00021902618999999982, "max": 0.014070295634999999, "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": "1716809780", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716812315" }, "total": 2535.615995832, "count": 1, "self": 0.43827539499989143, "children": { "run_training.setup": { "total": 0.08411408799997844, "count": 1, "self": 0.08411408799997844 }, "TrainerController.start_learning": { "total": 2535.093606349, "count": 1, "self": 4.46230303000948, "children": { "TrainerController._reset_env": { "total": 3.0503491509999776, "count": 1, "self": 3.0503491509999776 }, "TrainerController.advance": { "total": 2527.4621090279907, "count": 233472, "self": 4.738563134730612, "children": { "env_step": { "total": 1993.0355513970967, "count": 233472, "self": 1652.2929285780579, "children": { "SubprocessEnvManager._take_step": { "total": 337.7664729940626, "count": 233472, "self": 17.983147136046227, "children": { "TorchPolicy.evaluate": { "total": 319.7833258580164, "count": 223002, "self": 319.7833258580164 } } }, "workers": { "total": 2.9761498249762326, "count": 233472, "self": 0.0, "children": { "worker_root": { "total": 2527.5393352370193, "count": 233472, "is_parallel": true, "self": 1190.5627079170108, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008949650000431575, "count": 1, "is_parallel": true, "self": 0.00024078900014501414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006541759998981433, "count": 2, "is_parallel": true, "self": 0.0006541759998981433 } } }, "UnityEnvironment.step": { "total": 0.02985435999994479, "count": 1, "is_parallel": true, "self": 0.000389221000091311, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002046769999424214, "count": 1, "is_parallel": true, "self": 0.0002046769999424214 }, "communicator.exchange": { "total": 0.028484461999937594, "count": 1, "is_parallel": true, "self": 0.028484461999937594 }, "steps_from_proto": { "total": 0.0007759999999734646, "count": 1, "is_parallel": true, "self": 0.00019827800008442864, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005777219998890359, "count": 2, "is_parallel": true, "self": 0.0005777219998890359 } } } } } } }, "UnityEnvironment.step": { "total": 1336.9766273200084, "count": 233471, "is_parallel": true, "self": 40.351981717761646, "children": { "UnityEnvironment._generate_step_input": { "total": 87.71379069609907, "count": 233471, "is_parallel": true, "self": 87.71379069609907 }, "communicator.exchange": { "total": 1114.505760893121, "count": 233471, "is_parallel": true, "self": 1114.505760893121 }, "steps_from_proto": { "total": 94.40509401302666, "count": 233471, "is_parallel": true, "self": 35.96100898404961, "children": { "_process_rank_one_or_two_observation": { "total": 58.44408502897704, "count": 466942, "is_parallel": true, "self": 58.44408502897704 } } } } } } } } } } }, "trainer_advance": { "total": 529.6879944961636, "count": 233472, "self": 6.704380728222986, "children": { "process_trajectory": { "total": 165.96220885594005, "count": 233472, "self": 164.59656214594065, "children": { "RLTrainer._checkpoint": { "total": 1.365646709999396, "count": 10, "self": 1.365646709999396 } } }, "_update_policy": { "total": 357.02140491200055, "count": 97, "self": 292.88909449499124, "children": { "TorchPPOOptimizer.update": { "total": 64.13231041700931, "count": 2910, "self": 64.13231041700931 } } } } } } }, "trainer_threads": { "total": 1.017999693431193e-06, "count": 1, "self": 1.017999693431193e-06 }, "TrainerController._save_models": { "total": 0.11884412200015504, "count": 1, "self": 0.0018088360002366244, "children": { "RLTrainer._checkpoint": { "total": 0.11703528599991841, "count": 1, "self": 0.11703528599991841 } } } } } } }