{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15038228034973145, "min": 0.15038228034973145, "max": 1.3743131160736084, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4528.31103515625, "min": 4528.31103515625, "max": 41691.1640625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999974.0, "min": 29952.0, "max": 2999974.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999974.0, "min": 29952.0, "max": 2999974.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7555682063102722, "min": -0.15475746989250183, "max": 0.859150767326355, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 225.91488647460938, "min": -36.677520751953125, "max": 259.4635314941406, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00763231934979558, "min": -0.0070030526258051395, "max": 0.3295813798904419, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.2820634841918945, "min": -1.9082553386688232, "max": 79.75869750976562, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06996480564495348, "min": 0.0635249337354034, "max": 0.07332698063969256, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9795072790293489, "min": 0.5097892963785434, "max": 1.0714507637797699, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012787160794167512, "min": 0.0011003911749085144, "max": 0.017103391827688375, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17902025111834516, "min": 0.0154054764487192, "max": 0.24467762637205479, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5081637830261894e-06, "min": 1.5081637830261894e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.111429296236665e-05, "min": 2.111429296236665e-05, "max": 0.004052817149060966, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050268809523812, "min": 0.10050268809523812, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070376333333336, "min": 1.3962282666666668, "max": 2.7674522333333336, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0218540714285675e-05, "min": 6.0218540714285675e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008430595699999994, "min": 0.0008430595699999994, "max": 0.13509880943, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005964450538158417, "min": 0.005964450538158417, "max": 0.5031009316444397, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08350230753421783, "min": 0.08350230753421783, "max": 3.5217065811157227, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 215.03546099290782, "min": 215.03546099290782, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30320.0, "min": 15984.0, "max": 33050.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7423957307816398, "min": -1.0000000521540642, "max": 1.7862137327439913, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 245.6777980402112, "min": -27.638801611959934, "max": 245.6777980402112, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7423957307816398, "min": -1.0000000521540642, "max": 1.7862137327439913, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 245.6777980402112, "min": -27.638801611959934, "max": 245.6777980402112, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013373334838633908, "min": 0.013373334838633908, "max": 10.02461700886488, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.885640212247381, "min": 1.8233160735690035, "max": 160.39387214183807, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1780650669", "python_version": "3.8.20 (default, Oct 3 2024, 15:24:27) \n[GCC 11.2.0]", "command_line_arguments": "/home/alejandrolopezcordero01/miniconda3/envs/snowball-rl/bin/mlagents-learn ./ppo-huggyDog/ml-agents/config/ppo/PyramidsRND.yaml --env=./snowball-env/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids training --train --no-graphics --force --torch-device cpu", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1780654731" }, "total": 4061.50532707572, "count": 1, "self": 0.4778522551059723, "children": { "run_training.setup": { "total": 0.012601539492607117, "count": 1, "self": 0.012601539492607117 }, "TrainerController.start_learning": { "total": 4061.0148732811213, "count": 1, "self": 2.7678375989198685, "children": { "TrainerController._reset_env": { "total": 1.6024729013442993, "count": 1, "self": 1.6024729013442993 }, "TrainerController.advance": { "total": 4056.372522071004, "count": 195186, "self": 2.6755558401346207, "children": { "env_step": { "total": 2498.7542427629232, "count": 195186, "self": 2318.9857820123434, "children": { "SubprocessEnvManager._take_step": { "total": 178.02622325718403, "count": 195186, "self": 9.864511951804161, "children": { "TorchPolicy.evaluate": { "total": 168.16171130537987, "count": 187549, "self": 168.16171130537987 } } }, "workers": { "total": 1.7422374933958054, "count": 195186, "self": 0.0, "children": { "worker_root": { "total": 4056.2051654458046, "count": 195186, "is_parallel": true, "self": 1933.2795535624027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013557225465774536, "count": 1, "is_parallel": true, "self": 0.00038802623748779297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009676963090896606, "count": 8, "is_parallel": true, "self": 0.0009676963090896606 } } }, "UnityEnvironment.step": { "total": 0.037779852747917175, "count": 1, "is_parallel": true, "self": 0.0002923905849456787, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023037195205688477, "count": 1, "is_parallel": true, "self": 0.00023037195205688477 }, "communicator.exchange": { "total": 0.036429911851882935, "count": 1, "is_parallel": true, "self": 0.036429911851882935 }, "steps_from_proto": { "total": 0.0008271783590316772, "count": 1, "is_parallel": true, "self": 0.00019437074661254883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006328076124191284, "count": 8, "is_parallel": true, "self": 0.0006328076124191284 } } } } } } }, "UnityEnvironment.step": { "total": 2122.925611883402, "count": 195185, "is_parallel": true, "self": 49.46420207619667, "children": { "UnityEnvironment._generate_step_input": { "total": 35.146693751215935, "count": 195185, "is_parallel": true, "self": 35.146693751215935 }, "communicator.exchange": { "total": 1901.2837611883879, "count": 195185, "is_parallel": true, "self": 1901.2837611883879 }, "steps_from_proto": { "total": 137.0309548676014, "count": 195185, "is_parallel": true, "self": 30.470472112298012, "children": { "_process_rank_one_or_two_observation": { "total": 106.56048275530338, "count": 1561480, "is_parallel": true, "self": 106.56048275530338 } } } } } } } } } } }, "trainer_advance": { "total": 1554.942723467946, "count": 195186, "self": 4.506740972399712, "children": { "process_trajectory": { "total": 226.98552429676056, "count": 195186, "self": 225.42906093597412, "children": { "RLTrainer._checkpoint": { "total": 1.556463360786438, "count": 6, "self": 1.556463360786438 } } }, "_update_policy": { "total": 1323.4504581987858, "count": 1404, "self": 758.6627835333347, "children": { "TorchPPOOptimizer.update": { "total": 564.787674665451, "count": 68355, "self": 564.787674665451 } } } } } } }, "trainer_threads": { "total": 8.791685104370117e-07, "count": 1, "self": 8.791685104370117e-07 }, "TrainerController._save_models": { "total": 0.27203983068466187, "count": 1, "self": 0.03875349462032318, "children": { "RLTrainer._checkpoint": { "total": 0.23328633606433868, "count": 1, "self": 0.23328633606433868 } } } } } } }