{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.531305193901062, "min": 0.5177059769630432, "max": 1.475189447402954, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15964.658203125, "min": 15514.61328125, "max": 44751.34765625, "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": 0.4011560380458832, "min": -0.2643577456474304, "max": 0.4237026274204254, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.71328735351562, "min": -62.65278244018555, "max": 113.12860107421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.029258159920573235, "min": -0.16199925541877747, "max": 0.3529403805732727, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.928961277008057, "min": -40.66181182861328, "max": 85.41157531738281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06903998794515763, "min": 0.06483088139301692, "max": 0.07486551984135681, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9665598312322068, "min": 0.523377571840056, "max": 1.1229827976203521, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014720233573453728, "min": 0.000294675738673018, "max": 0.01582430648852774, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2060832700283522, "min": 0.0038307846027492336, "max": 0.22154029083938834, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.762233126907144e-06, "min": 7.762233126907144e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010867126377670002, "min": 0.00010867126377670002, "max": 0.0035074166308611994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258737857142859, "min": 0.10258737857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362233000000002, "min": 1.3886848, "max": 2.5691387999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026847911928571435, "min": 0.00026847911928571435, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003758707670000001, "min": 0.003758707670000001, "max": 0.11693696612, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01605222187936306, "min": 0.01605222187936306, "max": 0.5143592953681946, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22473111748695374, "min": 0.22473111748695374, "max": 3.6005148887634277, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 445.3333333333333, "min": 437.71830985915494, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30728.0, "min": 15984.0, "max": 33039.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3227159195188163, "min": -1.0000000521540642, "max": 1.509712477447465, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 91.26739844679832, "min": -31.997201666235924, "max": 98.91779863834381, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3227159195188163, "min": -1.0000000521540642, "max": 1.509712477447465, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 91.26739844679832, "min": -31.997201666235924, "max": 98.91779863834381, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07424974949706507, "min": 0.07424974949706507, "max": 10.464702650904655, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.12323271529749, "min": 4.984017043578206, "max": 167.4352424144745, "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": "1702911048", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702913194" }, "total": 2146.2735773100003, "count": 1, "self": 0.4876389000000927, "children": { "run_training.setup": { "total": 0.04868189799981337, "count": 1, "self": 0.04868189799981337 }, "TrainerController.start_learning": { "total": 2145.7372565120004, "count": 1, "self": 1.311686646045473, "children": { "TrainerController._reset_env": { "total": 3.203895201000023, "count": 1, "self": 3.203895201000023 }, "TrainerController.advance": { "total": 2141.135882227955, "count": 63496, "self": 1.395223884965617, "children": { "env_step": { "total": 1515.498661877029, "count": 63496, "self": 1384.113665240965, "children": { "SubprocessEnvManager._take_step": { "total": 130.56780180703845, "count": 63496, "self": 4.812029158074665, "children": { "TorchPolicy.evaluate": { "total": 125.75577264896378, "count": 62547, "self": 125.75577264896378 } } }, "workers": { "total": 0.8171948290255386, "count": 63496, "self": 0.0, "children": { "worker_root": { "total": 2140.8361350949576, "count": 63496, "is_parallel": true, "self": 875.360428842946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004563500999893222, "count": 1, "is_parallel": true, "self": 0.0034191890001693537, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011443119997238682, "count": 8, "is_parallel": true, "self": 0.0011443119997238682 } } }, "UnityEnvironment.step": { "total": 0.05788578200008487, "count": 1, "is_parallel": true, "self": 0.0006284920000325656, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046866200000295066, "count": 1, "is_parallel": true, "self": 0.00046866200000295066 }, "communicator.exchange": { "total": 0.055073672999924383, "count": 1, "is_parallel": true, "self": 0.055073672999924383 }, "steps_from_proto": { "total": 0.0017149550001249736, "count": 1, "is_parallel": true, "self": 0.00034230500023113564, "children": { "_process_rank_one_or_two_observation": { "total": 0.001372649999893838, "count": 8, "is_parallel": true, "self": 0.001372649999893838 } } } } } } }, "UnityEnvironment.step": { "total": 1265.4757062520116, "count": 63495, "is_parallel": true, "self": 34.924369249992424, "children": { "UnityEnvironment._generate_step_input": { "total": 24.851655528034826, "count": 63495, "is_parallel": true, "self": 24.851655528034826 }, "communicator.exchange": { "total": 1105.0549193699323, "count": 63495, "is_parallel": true, "self": 1105.0549193699323 }, "steps_from_proto": { "total": 100.644762104052, "count": 63495, "is_parallel": true, "self": 20.231194241019466, "children": { "_process_rank_one_or_two_observation": { "total": 80.41356786303254, "count": 507960, "is_parallel": true, "self": 80.41356786303254 } } } } } } } } } } }, "trainer_advance": { "total": 624.24199646596, "count": 63496, "self": 2.58713231896445, "children": { "process_trajectory": { "total": 129.22382142299352, "count": 63496, "self": 128.96917391499414, "children": { "RLTrainer._checkpoint": { "total": 0.25464750799937974, "count": 2, "self": 0.25464750799937974 } } }, "_update_policy": { "total": 492.43104272400205, "count": 448, "self": 292.7826216049739, "children": { "TorchPPOOptimizer.update": { "total": 199.64842111902817, "count": 22779, "self": 199.64842111902817 } } } } } } }, "trainer_threads": { "total": 1.0429998837935273e-06, "count": 1, "self": 1.0429998837935273e-06 }, "TrainerController._save_models": { "total": 0.08579139399989799, "count": 1, "self": 0.0013492889997905877, "children": { "RLTrainer._checkpoint": { "total": 0.0844421050001074, "count": 1, "self": 0.0844421050001074 } } } } } } }