{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36673593521118164, "min": 0.36431148648262024, "max": 1.430188775062561, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11060.755859375, "min": 10894.37109375, "max": 43386.20703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.614128589630127, "min": -0.10498394817113876, "max": 0.614128589630127, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 177.483154296875, "min": -25.301132202148438, "max": 177.483154296875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0003875170077662915, "min": -0.006516089662909508, "max": 0.1733197420835495, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.11199241876602173, "min": -1.7919247150421143, "max": 41.770057678222656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07044833040492529, "min": 0.06793646137981366, "max": 0.07526085881205896, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7044833040492529, "min": 0.4982913784808554, "max": 0.7405359965919043, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016815278137868702, "min": 0.0009372274771658244, "max": 0.016815278137868702, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16815278137868703, "min": 0.00850537928391339, "max": 0.16815278137868703, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.314637561819999e-06, "min": 7.314637561819999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.314637561819999e-05, "min": 7.314637561819999e-05, "max": 0.0023259887246705004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243818000000002, "min": 0.10243818000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.0243818000000002, "min": 0.9763622000000001, "max": 1.7753295000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025357418199999993, "min": 0.00025357418199999993, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0025357418199999995, "min": 0.0025357418199999995, "max": 0.07755541705, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008572550490498543, "min": 0.008433639071881771, "max": 0.2828032970428467, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08572550117969513, "min": 0.07785230875015259, "max": 1.9796230792999268, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 292.5327102803738, "min": 292.5327102803738, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31301.0, "min": 15984.0, "max": 32973.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.651370080135693, "min": -1.0000000521540642, "max": 1.660507352885447, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.69659857451916, "min": -27.814001739025116, "max": 176.69659857451916, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.651370080135693, "min": -1.0000000521540642, "max": 1.660507352885447, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.69659857451916, "min": -27.814001739025116, "max": 176.69659857451916, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02650154482752246, "min": 0.02650154482752246, "max": 6.0177089758217335, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.835665296544903, "min": 2.6516609785321634, "max": 96.28334361314774, "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": "1692627825", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692630402" }, "total": 2576.4502507760003, "count": 1, "self": 0.8923756310000499, "children": { "run_training.setup": { "total": 0.06422368400035339, "count": 1, "self": 0.06422368400035339 }, "TrainerController.start_learning": { "total": 2575.493651461, "count": 1, "self": 1.360992616128442, "children": { "TrainerController._reset_env": { "total": 4.52964624499964, "count": 1, "self": 4.52964624499964 }, "TrainerController.advance": { "total": 2569.4531833578717, "count": 64012, "self": 1.3977537267232947, "children": { "env_step": { "total": 1548.922745170055, "count": 64012, "self": 1439.9264165929922, "children": { "SubprocessEnvManager._take_step": { "total": 108.16985077405116, "count": 64012, "self": 4.760057118056466, "children": { "TorchPolicy.evaluate": { "total": 103.40979365599469, "count": 62543, "self": 103.40979365599469 } } }, "workers": { "total": 0.8264778030115849, "count": 64012, "self": 0.0, "children": { "worker_root": { "total": 2570.281450463085, "count": 64012, "is_parallel": true, "self": 1244.1538492179202, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002736176999860618, "count": 1, "is_parallel": true, "self": 0.0007984869998836075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019376899999770103, "count": 8, "is_parallel": true, "self": 0.0019376899999770103 } } }, "UnityEnvironment.step": { "total": 0.04879034199984744, "count": 1, "is_parallel": true, "self": 0.0006021699996381358, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004900160001852782, "count": 1, "is_parallel": true, "self": 0.0004900160001852782 }, "communicator.exchange": { "total": 0.0457208590000846, "count": 1, "is_parallel": true, "self": 0.0457208590000846 }, "steps_from_proto": { "total": 0.0019772969999394263, "count": 1, "is_parallel": true, "self": 0.0003963949998251337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015809020001142926, "count": 8, "is_parallel": true, "self": 0.0015809020001142926 } } } } } } }, "UnityEnvironment.step": { "total": 1326.127601245165, "count": 64011, "is_parallel": true, "self": 33.56096961828143, "children": { "UnityEnvironment._generate_step_input": { "total": 23.206274679962007, "count": 64011, "is_parallel": true, "self": 23.206274679962007 }, "communicator.exchange": { "total": 1164.1544746239952, "count": 64011, "is_parallel": true, "self": 1164.1544746239952 }, "steps_from_proto": { "total": 105.2058823229263, "count": 64011, "is_parallel": true, "self": 20.55290387672858, "children": { "_process_rank_one_or_two_observation": { "total": 84.65297844619772, "count": 512088, "is_parallel": true, "self": 84.65297844619772 } } } } } } } } } } }, "trainer_advance": { "total": 1019.1326844610935, "count": 64012, "self": 2.701204310162211, "children": { "process_trajectory": { "total": 112.04863130093054, "count": 64012, "self": 111.78617748493025, "children": { "RLTrainer._checkpoint": { "total": 0.2624538160002885, "count": 2, "self": 0.2624538160002885 } } }, "_update_policy": { "total": 904.3828488500008, "count": 309, "self": 584.6450213040061, "children": { "TorchPPOOptimizer.update": { "total": 319.7378275459946, "count": 38335, "self": 319.7378275459946 } } } } } } }, "trainer_threads": { "total": 1.4229999578674324e-06, "count": 1, "self": 1.4229999578674324e-06 }, "TrainerController._save_models": { "total": 0.14982781900016562, "count": 1, "self": 0.0020308519997342955, "children": { "RLTrainer._checkpoint": { "total": 0.14779696700043132, "count": 1, "self": 0.14779696700043132 } } } } } } }