{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8233450651168823, "min": 0.7984223365783691, "max": 1.3894301652908325, "count": 20 }, "Pyramids.Policy.Entropy.sum": { "value": 24766.21875, "min": 23709.94921875, "max": 42149.75390625, "count": 20 }, "Pyramids.Step.mean": { "value": 599937.0, "min": 29987.0, "max": 599937.0, "count": 20 }, "Pyramids.Step.sum": { "value": 599937.0, "min": 29987.0, "max": 599937.0, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03990941867232323, "min": -0.2289409339427948, "max": 0.06493476778268814, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 9.737897872924805, "min": -54.48794174194336, "max": 15.973953247070312, "count": 20 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016215212643146515, "min": 0.016164833679795265, "max": 0.5946663022041321, "count": 20 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.9565117359161377, "min": 3.9565117359161377, "max": 141.53057861328125, "count": 20 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06947956437641868, "min": 0.0666489455281856, "max": 0.07340738674391135, "count": 20 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9727139012698615, "min": 0.6074350104350869, "max": 1.0201817682936247, "count": 20 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005103617892065649, "min": 0.00011802643508214116, "max": 0.009582505592833681, "count": 20 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07145065048891909, "min": 0.0010622379157392704, "max": 0.08624255033550313, "count": 20 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.672918870964286e-06, "min": 7.672918870964286e-06, "max": 0.00029215083594972223, "count": 20 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001074208641935, "min": 0.0001074208641935, "max": 0.0027771610742796664, "count": 20 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255760714285715, "min": 0.10255760714285715, "max": 0.1973836111111111, "count": 20 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358065000000002, "min": 1.4358065000000002, "max": 1.9963236666666668, "count": 20 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002655049535714286, "min": 0.0002655049535714286, "max": 0.009738622750000002, "count": 20 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037170693500000003, "min": 0.0037170693500000003, "max": 0.0925794613, "count": 20 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015156647190451622, "min": 0.015006942674517632, "max": 0.4557708203792572, "count": 20 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2121930569410324, "min": 0.21009719371795654, "max": 4.101937294006348, "count": 20 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 856.5277777777778, "min": 751.6285714285714, "max": 999.0, "count": 20 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30835.0, "min": 16529.0, "max": 32867.0, "count": 20 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.23604576119354792, "min": -1.0000000521540642, "max": 0.21956567402396884, "count": 20 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -8.261601641774178, "min": -32.000001668930054, "max": 7.684798590838909, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.23604576119354792, "min": -1.0000000521540642, "max": 0.21956567402396884, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -8.261601641774178, "min": -32.000001668930054, "max": 7.684798590838909, "count": 20 }, "Pyramids.Policy.RndReward.mean": { "value": 0.13539667784103326, "min": 0.11727566726372711, "max": 8.225774183869362, "count": 20 }, "Pyramids.Policy.RndReward.sum": { "value": 4.738883724436164, "min": 4.104648354230449, "max": 148.0639353096485, "count": 20 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1659852097", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1659853187" }, "total": 1090.753050094, "count": 1, "self": 0.4787579189999178, "children": { "run_training.setup": { "total": 0.04378409000003103, "count": 1, "self": 0.04378409000003103 }, "TrainerController.start_learning": { "total": 1090.230508085, "count": 1, "self": 0.7525848999819118, "children": { "TrainerController._reset_env": { "total": 9.69543510599999, "count": 1, "self": 9.69543510599999 }, "TrainerController.advance": { "total": 1079.6859243150184, "count": 37821, "self": 0.8241268420299548, "children": { "env_step": { "total": 670.4507810920011, "count": 37821, "self": 609.7955857590207, "children": { "SubprocessEnvManager._take_step": { "total": 60.263676439977075, "count": 37821, "self": 2.62114733296994, "children": { "TorchPolicy.evaluate": { "total": 57.642529107007135, "count": 37554, "self": 19.93510012000837, "children": { "TorchPolicy.sample_actions": { "total": 37.707428986998764, "count": 37554, "self": 37.707428986998764 } } } } }, "workers": { "total": 0.3915188930032514, "count": 37821, "self": 0.0, "children": { "worker_root": { "total": 1087.9349839240058, "count": 37821, "is_parallel": true, "self": 535.6470072710106, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005467732999989039, "count": 1, "is_parallel": true, "self": 0.004173098000023856, "children": { "_process_rank_one_or_two_observation": { "total": 0.001294634999965183, "count": 8, "is_parallel": true, "self": 0.001294634999965183 } } }, "UnityEnvironment.step": { "total": 0.04794721700000082, "count": 1, "is_parallel": true, "self": 0.0005048500000270906, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004711689999794544, "count": 1, "is_parallel": true, "self": 0.0004711689999794544 }, "communicator.exchange": { "total": 0.04523462899999231, "count": 1, "is_parallel": true, "self": 0.04523462899999231 }, "steps_from_proto": { "total": 0.001736569000001964, "count": 1, "is_parallel": true, "self": 0.00043514500003993817, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013014239999620258, "count": 8, "is_parallel": true, "self": 0.0013014239999620258 } } } } } } }, "UnityEnvironment.step": { "total": 552.2879766529952, "count": 37820, "is_parallel": true, "self": 16.168420772010677, "children": { "UnityEnvironment._generate_step_input": { "total": 13.349130265982978, "count": 37820, "is_parallel": true, "self": 13.349130265982978 }, "communicator.exchange": { "total": 469.0925578330078, "count": 37820, "is_parallel": true, "self": 469.0925578330078 }, "steps_from_proto": { "total": 53.67786778199371, "count": 37820, "is_parallel": true, "self": 13.07753974403198, "children": { "_process_rank_one_or_two_observation": { "total": 40.60032803796173, "count": 302560, "is_parallel": true, "self": 40.60032803796173 } } } } } } } } } } }, "trainer_advance": { "total": 408.41101638098735, "count": 37821, "self": 1.2168836389824946, "children": { "process_trajectory": { "total": 91.3764676890047, "count": 37821, "self": 91.27221093400465, "children": { "RLTrainer._checkpoint": { "total": 0.10425675500005127, "count": 1, "self": 0.10425675500005127 } } }, "_update_policy": { "total": 315.81766505300016, "count": 241, "self": 123.1898380090172, "children": { "TorchPPOOptimizer.update": { "total": 192.62782704398296, "count": 13746, "self": 192.62782704398296 } } } } } } }, "trainer_threads": { "total": 1.4269999155658297e-06, "count": 1, "self": 1.4269999155658297e-06 }, "TrainerController._save_models": { "total": 0.09656233700002304, "count": 1, "self": 0.00172443800011024, "children": { "RLTrainer._checkpoint": { "total": 0.0948378989999128, "count": 1, "self": 0.0948378989999128 } } } } } } }