{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3438054919242859, "min": 0.3337518870830536, "max": 1.4662874937057495, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10303.1630859375, "min": 9964.49609375, "max": 44481.296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4352654814720154, "min": -0.11143050342798233, "max": 0.5023147463798523, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.08641052246094, "min": -26.854751586914062, "max": 133.1134033203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009223747998476028, "min": -0.008133110590279102, "max": 0.26480376720428467, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.4811882972717285, "min": -2.1552743911743164, "max": 63.817710876464844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06908356799402161, "min": 0.06337813112196866, "max": 0.0752445093459878, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9671699519163026, "min": 0.5094277558048074, "max": 1.0250495952786878, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015911807123661633, "min": 0.0007606788515447417, "max": 0.015911807123661633, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22276529973126288, "min": 0.0091281462185369, "max": 0.22276529973126288, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.592090326478574e-06, "min": 7.592090326478574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010628926457070004, "min": 0.00010628926457070004, "max": 0.0032528915157029, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253066428571429, "min": 0.10253066428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354293, "min": 1.3886848, "max": 2.4010806999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002628133621428572, "min": 0.0002628133621428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036793870700000007, "min": 0.0036793870700000007, "max": 0.10845128029000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014996377751231194, "min": 0.014996377751231194, "max": 0.389448881149292, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2099492847919464, "min": 0.2099492847919464, "max": 2.726142168045044, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 405.425, "min": 382.9382716049383, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32434.0, "min": 15984.0, "max": 33082.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.394509979709983, "min": -1.0000000521540642, "max": 1.594333307682604, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.56079837679863, "min": -30.702801667153835, "max": 126.9799979031086, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.394509979709983, "min": -1.0000000521540642, "max": 1.594333307682604, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.56079837679863, "min": -30.702801667153835, "max": 126.9799979031086, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.062216792117396835, "min": 0.06085209799790324, "max": 7.570364471524954, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.977343369391747, "min": 4.45782124674588, "max": 121.12583154439926, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679250797", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --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": "1679253061" }, "total": 2263.9188683109996, "count": 1, "self": 0.4418711259995689, "children": { "run_training.setup": { "total": 0.10268810299999132, "count": 1, "self": 0.10268810299999132 }, "TrainerController.start_learning": { "total": 2263.374309082, "count": 1, "self": 1.3654776310318084, "children": { "TrainerController._reset_env": { "total": 10.118552555000065, "count": 1, "self": 10.118552555000065 }, "TrainerController.advance": { "total": 2251.8005219059683, "count": 63629, "self": 1.5288829239702864, "children": { "env_step": { "total": 1597.8833186599863, "count": 63629, "self": 1483.5223066039962, "children": { "SubprocessEnvManager._take_step": { "total": 113.49478448898947, "count": 63629, "self": 5.049268336957425, "children": { "TorchPolicy.evaluate": { "total": 108.44551615203204, "count": 62555, "self": 108.44551615203204 } } }, "workers": { "total": 0.8662275670005783, "count": 63629, "self": 0.0, "children": { "worker_root": { "total": 2258.227945812976, "count": 63629, "is_parallel": true, "self": 896.6732364079978, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004980648999890036, "count": 1, "is_parallel": true, "self": 0.003441434999785997, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015392140001040389, "count": 8, "is_parallel": true, "self": 0.0015392140001040389 } } }, "UnityEnvironment.step": { "total": 0.055009745999996085, "count": 1, "is_parallel": true, "self": 0.0006671419998838246, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000581305000082466, "count": 1, "is_parallel": true, "self": 0.000581305000082466 }, "communicator.exchange": { "total": 0.051795309999988604, "count": 1, "is_parallel": true, "self": 0.051795309999988604 }, "steps_from_proto": { "total": 0.0019659890000411906, "count": 1, "is_parallel": true, "self": 0.00044362899984662363, "children": { "_process_rank_one_or_two_observation": { "total": 0.001522360000194567, "count": 8, "is_parallel": true, "self": 0.001522360000194567 } } } } } } }, "UnityEnvironment.step": { "total": 1361.5547094049782, "count": 63628, "is_parallel": true, "self": 31.90552756809234, "children": { "UnityEnvironment._generate_step_input": { "total": 23.81428990198401, "count": 63628, "is_parallel": true, "self": 23.81428990198401 }, "communicator.exchange": { "total": 1208.679651331985, "count": 63628, "is_parallel": true, "self": 1208.679651331985 }, "steps_from_proto": { "total": 97.15524060291693, "count": 63628, "is_parallel": true, "self": 21.190344126994432, "children": { "_process_rank_one_or_two_observation": { "total": 75.9648964759225, "count": 509024, "is_parallel": true, "self": 75.9648964759225 } } } } } } } } } } }, "trainer_advance": { "total": 652.3883203220119, "count": 63629, "self": 2.571983479961432, "children": { "process_trajectory": { "total": 125.30328017205, "count": 63629, "self": 124.97814080105002, "children": { "RLTrainer._checkpoint": { "total": 0.3251393709999775, "count": 2, "self": 0.3251393709999775 } } }, "_update_policy": { "total": 524.5130566700004, "count": 445, "self": 337.7054023230138, "children": { "TorchPPOOptimizer.update": { "total": 186.80765434698662, "count": 22812, "self": 186.80765434698662 } } } } } } }, "trainer_threads": { "total": 1.065999640559312e-06, "count": 1, "self": 1.065999640559312e-06 }, "TrainerController._save_models": { "total": 0.08975592400020105, "count": 1, "self": 0.0015053470001475944, "children": { "RLTrainer._checkpoint": { "total": 0.08825057700005345, "count": 1, "self": 0.08825057700005345 } } } } } } }