{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41224193572998047, "min": 0.41224193572998047, "max": 1.4232133626937866, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12347.470703125, "min": 12347.470703125, "max": 43174.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47863292694091797, "min": -0.12098627537488937, "max": 0.6040423512458801, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 128.75225830078125, "min": -29.157691955566406, "max": 167.31973266601562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02566806972026825, "min": 0.0021338188089430332, "max": 0.3815053105354309, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.90471076965332, "min": 0.5803987383842468, "max": 90.41675567626953, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06874033028309766, "min": 0.06450550111152956, "max": 0.0726938713029717, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9623646239633672, "min": 0.477583357200713, "max": 1.0716565478348867, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0143989032090065, "min": 0.000642932614123657, "max": 0.015834180997834273, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20158464492609102, "min": 0.006924524550552579, "max": 0.2303910442860797, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.289497570199999e-06, "min": 7.289497570199999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010205296598279998, "min": 0.00010205296598279998, "max": 0.0032544887151705, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024298, "min": 0.1024298, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340172, "min": 1.3691136000000002, "max": 2.443934, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002527370200000001, "min": 0.0002527370200000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003538318280000001, "min": 0.003538318280000001, "max": 0.10850446705, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011549736373126507, "min": 0.011549736373126507, "max": 0.3955830931663513, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16169631481170654, "min": 0.16169631481170654, "max": 2.7690815925598145, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 371.3125, "min": 337.36046511627904, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29705.0, "min": 15984.0, "max": 32327.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5286624782718718, "min": -1.0000000521540642, "max": 1.6393813818346623, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.29299826174974, "min": -32.000001668930054, "max": 140.98679883778095, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5286624782718718, "min": -1.0000000521540642, "max": 1.6393813818346623, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.29299826174974, "min": -32.000001668930054, "max": 140.98679883778095, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044625752406500394, "min": 0.04261604530621446, "max": 7.929269975051284, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5700601925200317, "min": 3.5700601925200317, "max": 126.86831960082054, "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": "1767842868", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1767845384" }, "total": 2515.879346885, "count": 1, "self": 0.5265149400006521, "children": { "run_training.setup": { "total": 0.026363607999883243, "count": 1, "self": 0.026363607999883243 }, "TrainerController.start_learning": { "total": 2515.3264683369994, "count": 1, "self": 1.6670974100243257, "children": { "TrainerController._reset_env": { "total": 1.6671148139998877, "count": 1, "self": 1.6671148139998877 }, "TrainerController.advance": { "total": 2511.9032832849753, "count": 63682, "self": 1.8347520801785322, "children": { "env_step": { "total": 1771.5350845779112, "count": 63682, "self": 1599.1162185718244, "children": { "SubprocessEnvManager._take_step": { "total": 171.4326844760585, "count": 63682, "self": 5.206103397183142, "children": { "TorchPolicy.evaluate": { "total": 166.22658107887537, "count": 62564, "self": 166.22658107887537 } } }, "workers": { "total": 0.9861815300282615, "count": 63682, "self": 0.0, "children": { "worker_root": { "total": 2510.5742345729695, "count": 63682, "is_parallel": true, "self": 1041.5905730218997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022360600000865816, "count": 1, "is_parallel": true, "self": 0.0007206569998743362, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015154030002122454, "count": 8, "is_parallel": true, "self": 0.0015154030002122454 } } }, "UnityEnvironment.step": { "total": 0.05520673399996667, "count": 1, "is_parallel": true, "self": 0.0005632809993585397, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004887230002168508, "count": 1, "is_parallel": true, "self": 0.0004887230002168508 }, "communicator.exchange": { "total": 0.052289777000169124, "count": 1, "is_parallel": true, "self": 0.052289777000169124 }, "steps_from_proto": { "total": 0.0018649530002221582, "count": 1, "is_parallel": true, "self": 0.0004017060000478523, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014632470001743059, "count": 8, "is_parallel": true, "self": 0.0014632470001743059 } } } } } } }, "UnityEnvironment.step": { "total": 1468.9836615510699, "count": 63681, "is_parallel": true, "self": 38.07368533003773, "children": { "UnityEnvironment._generate_step_input": { "total": 25.960759052917183, "count": 63681, "is_parallel": true, "self": 25.960759052917183 }, "communicator.exchange": { "total": 1279.8783573930268, "count": 63681, "is_parallel": true, "self": 1279.8783573930268 }, "steps_from_proto": { "total": 125.07085977508814, "count": 63681, "is_parallel": true, "self": 26.818076713208484, "children": { "_process_rank_one_or_two_observation": { "total": 98.25278306187965, "count": 509448, "is_parallel": true, "self": 98.25278306187965 } } } } } } } } } } }, "trainer_advance": { "total": 738.5334466268855, "count": 63682, "self": 3.225358753792989, "children": { "process_trajectory": { "total": 133.55798164208682, "count": 63682, "self": 133.28847864208637, "children": { "RLTrainer._checkpoint": { "total": 0.2695030000004408, "count": 2, "self": 0.2695030000004408 } } }, "_update_policy": { "total": 601.7501062310057, "count": 443, "self": 333.61280337000426, "children": { "TorchPPOOptimizer.update": { "total": 268.13730286100144, "count": 22800, "self": 268.13730286100144 } } } } } } }, "trainer_threads": { "total": 1.2209993656142615e-06, "count": 1, "self": 1.2209993656142615e-06 }, "TrainerController._save_models": { "total": 0.08897160700053064, "count": 1, "self": 0.0012226310000187368, "children": { "RLTrainer._checkpoint": { "total": 0.0877489760005119, "count": 1, "self": 0.0877489760005119 } } } } } } }