{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45122894644737244, "min": 0.45122894644737244, "max": 1.408017873764038, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13536.8681640625, "min": 13536.8681640625, "max": 42713.62890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29878.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29878.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6907827258110046, "min": -0.08872498571872711, "max": 0.7070160508155823, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 196.87307739257812, "min": -21.382720947265625, "max": 202.91360473632812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018096428364515305, "min": -0.015022831037640572, "max": 0.4864693284034729, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.157482147216797, "min": -4.116255760192871, "max": 115.29322814941406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07037781884511268, "min": 0.06602629360984828, "max": 0.07509797458899103, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9852894638315776, "min": 0.5001997597659096, "max": 1.1264696188348655, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016544400647814785, "min": 0.0005133628755334453, "max": 0.01683184536751451, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.231621609069407, "min": 0.006673717381934789, "max": 0.2364673478587065, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.451218944864287e-06, "min": 7.451218944864287e-06, "max": 0.0002952360873022571, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010431706522810002, "min": 0.00010431706522810002, "max": 0.0036335413888196, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248370714285714, "min": 0.10248370714285714, "max": 0.19841202857142856, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347718999999999, "min": 1.3888842, "max": 2.6111804000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002581223435714287, "min": 0.0002581223435714287, "max": 0.009841361654285714, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036137128100000014, "min": 0.0036137128100000014, "max": 0.12113692196, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008221691474318504, "min": 0.008221691474318504, "max": 0.5074041485786438, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11510368436574936, "min": 0.11510368436574936, "max": 3.5518290996551514, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 252.33035714285714, "min": 252.33035714285714, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28261.0, "min": 16677.0, "max": 33306.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7298053432522076, "min": -0.9999125530011952, "max": 1.7450956344604491, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 193.73819844424725, "min": -31.997201696038246, "max": 200.68599796295166, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7298053432522076, "min": -0.9999125530011952, "max": 1.7450956344604491, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 193.73819844424725, "min": -31.997201696038246, "max": 200.68599796295166, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.021454686766836466, "min": 0.021454686766836466, "max": 10.772113094435019, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4029249178856844, "min": 2.4029249178856844, "max": 183.12592260539532, "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": "1694838457", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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", "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": "1694840057" }, "total": 1599.6554839079995, "count": 1, "self": 0.3722044899991488, "children": { "run_training.setup": { "total": 0.03913120900006106, "count": 1, "self": 0.03913120900006106 }, "TrainerController.start_learning": { "total": 1599.2441482090003, "count": 1, "self": 1.3094990510157913, "children": { "TrainerController._reset_env": { "total": 4.254138626999975, "count": 1, "self": 4.254138626999975 }, "TrainerController.advance": { "total": 1593.588115723985, "count": 64148, "self": 1.2619128559758792, "children": { "env_step": { "total": 1025.5919427570038, "count": 64148, "self": 926.8933200229421, "children": { "SubprocessEnvManager._take_step": { "total": 97.93429947803816, "count": 64148, "self": 4.259726400996442, "children": { "TorchPolicy.evaluate": { "total": 93.67457307704171, "count": 62551, "self": 93.67457307704171 } } }, "workers": { "total": 0.7643232560235447, "count": 64148, "self": 0.0, "children": { "worker_root": { "total": 1596.9442376879265, "count": 64148, "is_parallel": true, "self": 758.8825223579825, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016897770001378376, "count": 1, "is_parallel": true, "self": 0.0005008920002183004, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011888849999195372, "count": 8, "is_parallel": true, "self": 0.0011888849999195372 } } }, "UnityEnvironment.step": { "total": 0.03568901500011634, "count": 1, "is_parallel": true, "self": 0.0003486360001261346, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003295510000498325, "count": 1, "is_parallel": true, "self": 0.0003295510000498325 }, "communicator.exchange": { "total": 0.03319216399995639, "count": 1, "is_parallel": true, "self": 0.03319216399995639 }, "steps_from_proto": { "total": 0.0018186639999839826, "count": 1, "is_parallel": true, "self": 0.00025715199853948434, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015615120014444983, "count": 8, "is_parallel": true, "self": 0.0015615120014444983 } } } } } } }, "UnityEnvironment.step": { "total": 838.061715329944, "count": 64147, "is_parallel": true, "self": 20.9702945079066, "children": { "UnityEnvironment._generate_step_input": { "total": 14.827294491002249, "count": 64147, "is_parallel": true, "self": 14.827294491002249 }, "communicator.exchange": { "total": 739.8008039840274, "count": 64147, "is_parallel": true, "self": 739.8008039840274 }, "steps_from_proto": { "total": 62.46332234700776, "count": 64147, "is_parallel": true, "self": 12.927339026144637, "children": { "_process_rank_one_or_two_observation": { "total": 49.535983320863124, "count": 513176, "is_parallel": true, "self": 49.535983320863124 } } } } } } } } } } }, "trainer_advance": { "total": 566.7342601110054, "count": 64148, "self": 2.4730441800506924, "children": { "process_trajectory": { "total": 96.09574176095339, "count": 64148, "self": 95.88315713895327, "children": { "RLTrainer._checkpoint": { "total": 0.21258462200012218, "count": 2, "self": 0.21258462200012218 } } }, "_update_policy": { "total": 468.1654741700013, "count": 458, "self": 298.3917277840128, "children": { "TorchPPOOptimizer.update": { "total": 169.7737463859885, "count": 22794, "self": 169.7737463859885 } } } } } } }, "trainer_threads": { "total": 8.950000847107731e-07, "count": 1, "self": 8.950000847107731e-07 }, "TrainerController._save_models": { "total": 0.09239391199935199, "count": 1, "self": 0.001400793998982408, "children": { "RLTrainer._checkpoint": { "total": 0.09099311800036958, "count": 1, "self": 0.09099311800036958 } } } } } } }