{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5609207153320312, "min": 0.5550739169120789, "max": 1.395443320274353, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16710.94921875, "min": 16710.94921875, "max": 42332.16796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29900.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29900.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5511177182197571, "min": -0.08345665037631989, "max": 0.5641608238220215, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.86407470703125, "min": -20.113052368164062, "max": 155.14422607421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012479162774980068, "min": -0.009399117901921272, "max": 0.32309338450431824, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.5066447257995605, "min": -2.5753583908081055, "max": 77.54241180419922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0673223896599727, "min": 0.06573836891947794, "max": 0.07376802339085999, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9425134552396177, "min": 0.571805765652447, "max": 1.1059773351270112, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01522596007907086, "min": 0.000799258206186218, "max": 0.01663943660678342, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21316344110699204, "min": 0.009591098474234616, "max": 0.24959154910175127, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.686226009385717e-06, "min": 7.686226009385717e-06, "max": 0.00029500035166655, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010760716413140004, "min": 0.00010760716413140004, "max": 0.0036322093892635996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256204285714286, "min": 0.10256204285714286, "max": 0.19833345, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358686, "min": 1.4358686, "max": 2.6107364, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002659480814285716, "min": 0.0002659480814285716, "max": 0.009833511654999998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003723273140000002, "min": 0.003723273140000002, "max": 0.12109256635999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013258623890578747, "min": 0.013111588545143604, "max": 0.47583431005477905, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1856207400560379, "min": 0.183562234044075, "max": 3.8066744804382324, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 333.9512195121951, "min": 333.9512195121951, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27384.0, "min": 17082.0, "max": 33095.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.64164876174636, "min": -0.9999419873760592, "max": 1.64164876174636, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.61519846320152, "min": -30.998201608657837, "max": 138.3573983311653, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.64164876174636, "min": -0.9999419873760592, "max": 1.64164876174636, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.61519846320152, "min": -30.998201608657837, "max": 138.3573983311653, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04589055652131054, "min": 0.04589055652131054, "max": 8.64536305434174, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.763025634747464, "min": 3.763025634747464, "max": 155.61653497815132, "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": "1687112111", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 Training --no-graphics --force", "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": "1687114573" }, "total": 2462.021744918, "count": 1, "self": 1.1084785479988568, "children": { "run_training.setup": { "total": 0.04174876000070071, "count": 1, "self": 0.04174876000070071 }, "TrainerController.start_learning": { "total": 2460.8715176100004, "count": 1, "self": 1.7122806310508167, "children": { "TrainerController._reset_env": { "total": 4.725388283999564, "count": 1, "self": 4.725388283999564 }, "TrainerController.advance": { "total": 2454.317271210949, "count": 63913, "self": 1.7505984818926663, "children": { "env_step": { "total": 1784.853047866044, "count": 63913, "self": 1662.006885662051, "children": { "SubprocessEnvManager._take_step": { "total": 121.88977028702993, "count": 63913, "self": 5.282818576911268, "children": { "TorchPolicy.evaluate": { "total": 116.60695171011866, "count": 62553, "self": 116.60695171011866 } } }, "workers": { "total": 0.9563919169631845, "count": 63913, "self": 0.0, "children": { "worker_root": { "total": 2454.4542479959346, "count": 63913, "is_parallel": true, "self": 920.7708041019341, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019115130007776315, "count": 1, "is_parallel": true, "self": 0.0005995849996907054, "children": { "_process_rank_one_or_two_observation": { "total": 0.001311928001086926, "count": 8, "is_parallel": true, "self": 0.001311928001086926 } } }, "UnityEnvironment.step": { "total": 0.1024508220007192, "count": 1, "is_parallel": true, "self": 0.0006324500009213807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045807599963154644, "count": 1, "is_parallel": true, "self": 0.00045807599963154644 }, "communicator.exchange": { "total": 0.09935798200058343, "count": 1, "is_parallel": true, "self": 0.09935798200058343 }, "steps_from_proto": { "total": 0.0020023139995828387, "count": 1, "is_parallel": true, "self": 0.00035135199959768215, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016509619999851566, "count": 8, "is_parallel": true, "self": 0.0016509619999851566 } } } } } } }, "UnityEnvironment.step": { "total": 1533.6834438940004, "count": 63912, "is_parallel": true, "self": 36.33494097501625, "children": { "UnityEnvironment._generate_step_input": { "total": 24.477291079922907, "count": 63912, "is_parallel": true, "self": 24.477291079922907 }, "communicator.exchange": { "total": 1362.447713341011, "count": 63912, "is_parallel": true, "self": 1362.447713341011 }, "steps_from_proto": { "total": 110.42349849805032, "count": 63912, "is_parallel": true, "self": 22.334162450102667, "children": { "_process_rank_one_or_two_observation": { "total": 88.08933604794765, "count": 511296, "is_parallel": true, "self": 88.08933604794765 } } } } } } } } } } }, "trainer_advance": { "total": 667.7136248630122, "count": 63913, "self": 3.0219805721462762, "children": { "process_trajectory": { "total": 113.15612898786003, "count": 63913, "self": 112.93090543186008, "children": { "RLTrainer._checkpoint": { "total": 0.22522355599994626, "count": 2, "self": 0.22522355599994626 } } }, "_update_policy": { "total": 551.5355153030059, "count": 457, "self": 354.64018996400864, "children": { "TorchPPOOptimizer.update": { "total": 196.89532533899728, "count": 22806, "self": 196.89532533899728 } } } } } } }, "trainer_threads": { "total": 1.1910005923709832e-06, "count": 1, "self": 1.1910005923709832e-06 }, "TrainerController._save_models": { "total": 0.11657629300043482, "count": 1, "self": 0.001025455000672082, "children": { "RLTrainer._checkpoint": { "total": 0.11555083799976273, "count": 1, "self": 0.11555083799976273 } } } } } } }