{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8240864872932434, "min": 0.8112577795982361, "max": 1.4814174175262451, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 24696.224609375, "min": 24467.53515625, "max": 44940.27734375, "count": 16 }, "Pyramids.Step.mean": { "value": 479976.0, "min": 29952.0, "max": 479976.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479976.0, "min": 29952.0, "max": 479976.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.14563710987567902, "min": -0.09152958542108536, "max": 0.14563710987567902, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 36.263641357421875, "min": -21.967100143432617, "max": 36.263641357421875, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.058837827295064926, "min": 0.02931838296353817, "max": 0.40576598048210144, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.650618553161621, "min": 7.241640567779541, "max": 96.16653442382812, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06551292970675796, "min": 0.06551292970675796, "max": 0.0724271701955688, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9171810158946113, "min": 0.48936093182687046, "max": 1.0029008920132139, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009125758486782612, "min": 0.0007770561829373332, "max": 0.009781751784906926, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12776061881495657, "min": 0.007770561829373332, "max": 0.13694452498869697, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0743850228271425e-05, "min": 2.0743850228271425e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00029041390319579994, "min": 0.00029041390319579994, "max": 0.0028154356615216003, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1069145857142857, "min": 0.1069145857142857, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4968042, "min": 1.3382272, "max": 2.3384784000000005, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007007671128571428, "min": 0.0007007671128571428, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.00981073958, "min": 0.00981073958, "max": 0.09389399216, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02078682743012905, "min": 0.02078682743012905, "max": 0.47662487626075745, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2910155951976776, "min": 0.2910155951976776, "max": 3.336374044418335, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 725.1395348837209, "min": 695.3636363636364, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31181.0, "min": 15984.0, "max": 32672.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5769627530907475, "min": -1.0000000521540642, "max": 0.5771090549162843, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 24.809398382902145, "min": -32.000001668930054, "max": 25.39279841631651, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5769627530907475, "min": -1.0000000521540642, "max": 0.5771090549162843, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 24.809398382902145, "min": -32.000001668930054, "max": 25.39279841631651, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.15822068458358043, "min": 0.15822068458358043, "max": 10.198477046564221, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 6.803489437093958, "min": 6.428280530730262, "max": 163.17563274502754, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1657432745", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1657433776" }, "total": 1030.7415311660002, "count": 1, "self": 0.4772998510002253, "children": { "run_training.setup": { "total": 0.04340227100010452, "count": 1, "self": 0.04340227100010452 }, "TrainerController.start_learning": { "total": 1030.2208290439999, "count": 1, "self": 0.6730740399914339, "children": { "TrainerController._reset_env": { "total": 10.226432853999995, "count": 1, "self": 10.226432853999995 }, "TrainerController.advance": { "total": 1019.2264794710088, "count": 31649, "self": 0.719046518056075, "children": { "env_step": { "total": 656.2663542909729, "count": 31649, "self": 602.9678051790122, "children": { "SubprocessEnvManager._take_step": { "total": 52.933573677975346, "count": 31649, "self": 2.3392168470313663, "children": { "TorchPolicy.evaluate": { "total": 50.59435683094398, "count": 31308, "self": 17.57771765294251, "children": { "TorchPolicy.sample_actions": { "total": 33.01663917800147, "count": 31308, "self": 33.01663917800147 } } } } }, "workers": { "total": 0.36497543398536436, "count": 31649, "self": 0.0, "children": { "worker_root": { "total": 1028.136700980038, "count": 31649, "is_parallel": true, "self": 476.09514795201403, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005482437999944523, "count": 1, "is_parallel": true, "self": 0.004173504000391404, "children": { "_process_rank_one_or_two_observation": { "total": 0.001308933999553119, "count": 8, "is_parallel": true, "self": 0.001308933999553119 } } }, "UnityEnvironment.step": { "total": 0.04943937300004109, "count": 1, "is_parallel": true, "self": 0.0005826089998208772, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047796900003049814, "count": 1, "is_parallel": true, "self": 0.00047796900003049814 }, "communicator.exchange": { "total": 0.04668553900000916, "count": 1, "is_parallel": true, "self": 0.04668553900000916 }, "steps_from_proto": { "total": 0.0016932560001805541, "count": 1, "is_parallel": true, "self": 0.00043974999994134123, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012535060002392129, "count": 8, "is_parallel": true, "self": 0.0012535060002392129 } } } } } } }, "UnityEnvironment.step": { "total": 552.041553028024, "count": 31648, "is_parallel": true, "self": 14.455718548986624, "children": { "UnityEnvironment._generate_step_input": { "total": 11.97533555800942, "count": 31648, "is_parallel": true, "self": 11.97533555800942 }, "communicator.exchange": { "total": 477.8063062820247, "count": 31648, "is_parallel": true, "self": 477.8063062820247 }, "steps_from_proto": { "total": 47.804192639003304, "count": 31648, "is_parallel": true, "self": 11.781612921938631, "children": { "_process_rank_one_or_two_observation": { "total": 36.02257971706467, "count": 253184, "is_parallel": true, "self": 36.02257971706467 } } } } } } } } } } }, "trainer_advance": { "total": 362.2410786619798, "count": 31649, "self": 1.20137732094895, "children": { "process_trajectory": { "total": 81.8424588180269, "count": 31649, "self": 81.73584209602723, "children": { "RLTrainer._checkpoint": { "total": 0.10661672199967143, "count": 1, "self": 0.10661672199967143 } } }, "_update_policy": { "total": 279.197242523004, "count": 210, "self": 109.81181349898179, "children": { "TorchPPOOptimizer.update": { "total": 169.3854290240222, "count": 11430, "self": 169.3854290240222 } } } } } } }, "trainer_threads": { "total": 1.0909998309216462e-06, "count": 1, "self": 1.0909998309216462e-06 }, "TrainerController._save_models": { "total": 0.09484158799978104, "count": 1, "self": 0.0015464620000784635, "children": { "RLTrainer._checkpoint": { "total": 0.09329512599970258, "count": 1, "self": 0.09329512599970258 } } } } } } }