{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6736977100372314, "min": 0.6198792457580566, "max": 1.4141618013381958, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20286.384765625, "min": 18774.90234375, "max": 42900.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.02592300996184349, "min": -0.10772595554590225, "max": 0.02592300996184349, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 6.402983665466309, "min": -25.961956024169922, "max": 6.402983665466309, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02117227576673031, "min": 0.004633665084838867, "max": 0.6760766506195068, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.229552268981934, "min": 1.1259806156158447, "max": 160.23016357421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06769739676742026, "min": 0.06341377033498882, "max": 0.07244526982478579, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9477635547438836, "min": 0.49909575964222486, "max": 1.070488970690206, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00458868943730015, "min": 0.00011175098238129912, "max": 0.023822861587580835, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0642416521222021, "min": 0.0015645137533381876, "max": 0.16676003111306584, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.265369006814283e-06, "min": 7.265369006814283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010171516609539996, "min": 0.00010171516609539996, "max": 0.0033711007762997993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242175714285714, "min": 0.10242175714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339046, "min": 1.3886848, "max": 2.442973, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002519335385714285, "min": 0.0002519335385714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035270695399999986, "min": 0.0035270695399999986, "max": 0.11238764998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01812569424510002, "min": 0.01812569424510002, "max": 0.7999270558357239, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2537597119808197, "min": 0.2537597119808197, "max": 5.599489212036133, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 829.0263157894736, "min": 811.6111111111111, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31503.0, "min": 15984.0, "max": 33238.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.14521056668538795, "min": -1.0000000521540642, "max": -0.058109141208908775, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -5.518001534044743, "min": -30.597001671791077, "max": -1.9176016598939896, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.14521056668538795, "min": -1.0000000521540642, "max": -0.058109141208908775, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -5.518001534044743, "min": -30.597001671791077, "max": -1.9176016598939896, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.15536519685625344, "min": 0.15536519685625344, "max": 17.52510759420693, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.903877480537631, "min": 5.506261245813221, "max": 280.40172150731087, "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": "1722173776", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722176148" }, "total": 2372.5388752540002, "count": 1, "self": 0.5332041679998838, "children": { "run_training.setup": { "total": 0.05503801700024269, "count": 1, "self": 0.05503801700024269 }, "TrainerController.start_learning": { "total": 2371.950633069, "count": 1, "self": 1.9759006100121042, "children": { "TrainerController._reset_env": { "total": 2.142032736999681, "count": 1, "self": 2.142032736999681 }, "TrainerController.advance": { "total": 2367.739921567988, "count": 63204, "self": 2.0344011850661445, "children": { "env_step": { "total": 1678.7388236719694, "count": 63204, "self": 1504.6707382740155, "children": { "SubprocessEnvManager._take_step": { "total": 172.85837494195266, "count": 63204, "self": 5.987318446861536, "children": { "TorchPolicy.evaluate": { "total": 166.87105649509112, "count": 62565, "self": 166.87105649509112 } } }, "workers": { "total": 1.2097104560011758, "count": 63204, "self": 0.0, "children": { "worker_root": { "total": 2365.6948671360406, "count": 63204, "is_parallel": true, "self": 1015.012387977114, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022589320001316082, "count": 1, "is_parallel": true, "self": 0.000703372000316449, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015555599998151592, "count": 8, "is_parallel": true, "self": 0.0015555599998151592 } } }, "UnityEnvironment.step": { "total": 0.05585919100030878, "count": 1, "is_parallel": true, "self": 0.0007087430008141382, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005386119996728667, "count": 1, "is_parallel": true, "self": 0.0005386119996728667 }, "communicator.exchange": { "total": 0.050047713999902044, "count": 1, "is_parallel": true, "self": 0.050047713999902044 }, "steps_from_proto": { "total": 0.004564121999919735, "count": 1, "is_parallel": true, "self": 0.0030152290000842186, "children": { "_process_rank_one_or_two_observation": { "total": 0.001548892999835516, "count": 8, "is_parallel": true, "self": 0.001548892999835516 } } } } } } }, "UnityEnvironment.step": { "total": 1350.6824791589265, "count": 63203, "is_parallel": true, "self": 40.62036701064244, "children": { "UnityEnvironment._generate_step_input": { "total": 27.47282384003529, "count": 63203, "is_parallel": true, "self": 27.47282384003529 }, "communicator.exchange": { "total": 1167.1019556301749, "count": 63203, "is_parallel": true, "self": 1167.1019556301749 }, "steps_from_proto": { "total": 115.48733267807393, "count": 63203, "is_parallel": true, "self": 25.00317458384552, "children": { "_process_rank_one_or_two_observation": { "total": 90.4841580942284, "count": 505624, "is_parallel": true, "self": 90.4841580942284 } } } } } } } } } } }, "trainer_advance": { "total": 686.9666967109524, "count": 63204, "self": 3.582054438896648, "children": { "process_trajectory": { "total": 141.5031872690497, "count": 63204, "self": 141.28295461604876, "children": { "RLTrainer._checkpoint": { "total": 0.22023265300094863, "count": 2, "self": 0.22023265300094863 } } }, "_update_policy": { "total": 541.8814550030061, "count": 446, "self": 318.56586804496374, "children": { "TorchPPOOptimizer.update": { "total": 223.31558695804233, "count": 22905, "self": 223.31558695804233 } } } } } } }, "trainer_threads": { "total": 1.0260000635753386e-06, "count": 1, "self": 1.0260000635753386e-06 }, "TrainerController._save_models": { "total": 0.09277712800030713, "count": 1, "self": 0.0014536150001731585, "children": { "RLTrainer._checkpoint": { "total": 0.09132351300013397, "count": 1, "self": 0.09132351300013397 } } } } } } }