{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35916367173194885, "min": 0.35916367173194885, "max": 1.5352976322174072, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10843.869140625, "min": 10843.869140625, "max": 46574.7890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6247797012329102, "min": -0.1523773968219757, "max": 0.6904860138893127, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.18788146972656, "min": -36.113441467285156, "max": 200.24093627929688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03212345018982887, "min": -0.025862297043204308, "max": 0.29317232966423035, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.058813095092773, "min": -7.267305374145508, "max": 69.48184204101562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06649921104655647, "min": 0.06649921104655647, "max": 0.07583984071530692, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9309889546517905, "min": 0.48044906557827316, "max": 1.0661472712721054, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015261379526540015, "min": 0.00037708136872773176, "max": 0.017823695468859643, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21365931337156022, "min": 0.004147895056005049, "max": 0.263527518104335, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.45464751515e-06, "min": 7.45464751515e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001043650652121, "min": 0.0001043650652121, "max": 0.0031392461535847006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248485000000003, "min": 0.10248485000000003, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347879000000003, "min": 1.3691136000000002, "max": 2.4011228, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025823651500000007, "min": 0.00025823651500000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003615311210000001, "min": 0.003615311210000001, "max": 0.10466688847, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011630422435700893, "min": 0.011612421832978725, "max": 0.2621047794818878, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16282591223716736, "min": 0.162573903799057, "max": 1.8347333669662476, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 288.8, "min": 288.8, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28880.0, "min": 15984.0, "max": 33034.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6711839861422777, "min": -1.0000000521540642, "max": 1.689229400134554, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 167.11839861422777, "min": -32.000001668930054, "max": 172.30139881372452, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6711839861422777, "min": -1.0000000521540642, "max": 1.689229400134554, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 167.11839861422777, "min": -32.000001668930054, "max": 172.30139881372452, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03486514454241842, "min": 0.03486514454241842, "max": 5.360377009958029, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.486514454241842, "min": 3.486514454241842, "max": 85.76603215932846, "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": "1685981017", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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", "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": "1685983230" }, "total": 2213.4242458090002, "count": 1, "self": 0.77372498800014, "children": { "run_training.setup": { "total": 0.04218314900003861, "count": 1, "self": 0.04218314900003861 }, "TrainerController.start_learning": { "total": 2212.608337672, "count": 1, "self": 1.3409053449076964, "children": { "TrainerController._reset_env": { "total": 5.002522475999967, "count": 1, "self": 5.002522475999967 }, "TrainerController.advance": { "total": 2206.1253407350914, "count": 63954, "self": 1.3470337251283127, "children": { "env_step": { "total": 1576.5241454280194, "count": 63954, "self": 1470.254612979036, "children": { "SubprocessEnvManager._take_step": { "total": 105.44092440994268, "count": 63954, "self": 4.676467569959414, "children": { "TorchPolicy.evaluate": { "total": 100.76445683998327, "count": 62563, "self": 100.76445683998327 } } }, "workers": { "total": 0.8286080390407733, "count": 63954, "self": 0.0, "children": { "worker_root": { "total": 2207.4895596070514, "count": 63954, "is_parallel": true, "self": 848.1161771770408, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024054339999111107, "count": 1, "is_parallel": true, "self": 0.0006625199998779863, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017429140000331245, "count": 8, "is_parallel": true, "self": 0.0017429140000331245 } } }, "UnityEnvironment.step": { "total": 0.04624083800013068, "count": 1, "is_parallel": true, "self": 0.0005112580001878086, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004730709999876126, "count": 1, "is_parallel": true, "self": 0.0004730709999876126 }, "communicator.exchange": { "total": 0.04351633999999649, "count": 1, "is_parallel": true, "self": 0.04351633999999649 }, "steps_from_proto": { "total": 0.0017401689999587688, "count": 1, "is_parallel": true, "self": 0.0003513759995712462, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013887930003875226, "count": 8, "is_parallel": true, "self": 0.0013887930003875226 } } } } } } }, "UnityEnvironment.step": { "total": 1359.3733824300107, "count": 63953, "is_parallel": true, "self": 31.404930342913076, "children": { "UnityEnvironment._generate_step_input": { "total": 22.359911578010042, "count": 63953, "is_parallel": true, "self": 22.359911578010042 }, "communicator.exchange": { "total": 1209.032719148057, "count": 63953, "is_parallel": true, "self": 1209.032719148057 }, "steps_from_proto": { "total": 96.57582136103065, "count": 63953, "is_parallel": true, "self": 19.712231652878927, "children": { "_process_rank_one_or_two_observation": { "total": 76.86358970815172, "count": 511624, "is_parallel": true, "self": 76.86358970815172 } } } } } } } } } } }, "trainer_advance": { "total": 628.2541615819439, "count": 63954, "self": 2.5495651179201104, "children": { "process_trajectory": { "total": 106.1508125700243, "count": 63954, "self": 105.90639588002477, "children": { "RLTrainer._checkpoint": { "total": 0.24441668999952526, "count": 2, "self": 0.24441668999952526 } } }, "_update_policy": { "total": 519.5537838939995, "count": 441, "self": 337.9785042679864, "children": { "TorchPPOOptimizer.update": { "total": 181.57527962601307, "count": 22836, "self": 181.57527962601307 } } } } } } }, "trainer_threads": { "total": 1.347000306850532e-06, "count": 1, "self": 1.347000306850532e-06 }, "TrainerController._save_models": { "total": 0.13956776900022305, "count": 1, "self": 0.0018047390003630426, "children": { "RLTrainer._checkpoint": { "total": 0.13776302999986, "count": 1, "self": 0.13776302999986 } } } } } } }