{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33868148922920227, "min": 0.33868148922920227, "max": 1.3777344226837158, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10117.09375, "min": 10117.09375, "max": 41794.953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3354318141937256, "min": -0.09333772957324982, "max": 0.42438462376594543, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 88.55400085449219, "min": -22.40105438232422, "max": 114.58384704589844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012628663331270218, "min": -0.05736546590924263, "max": 0.29756245017051697, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3339672088623047, "min": -14.915020942687988, "max": 70.71188354492188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06330667053851825, "min": 0.06330667053851825, "max": 0.07276136423960063, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8862933875392555, "min": 0.4784811694337585, "max": 1.0192073220193074, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01199462507420245, "min": 0.000681335807328648, "max": 0.01445068260196306, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1679247510388343, "min": 0.0047693506513005355, "max": 0.20230955642748286, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.680526011285714e-06, "min": 7.680526011285714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000107527364158, "min": 0.000107527364158, "max": 0.003375223974925399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256014285714286, "min": 0.10256014285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.435842, "min": 1.3691136000000002, "max": 2.4853102000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026575827142857146, "min": 0.00026575827142857146, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037206158000000003, "min": 0.0037206158000000003, "max": 0.11252495254, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010018088854849339, "min": 0.010018088854849339, "max": 0.468504935503006, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1402532458305359, "min": 0.1402532458305359, "max": 3.2795345783233643, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 480.0983606557377, "min": 434.72463768115944, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29286.0, "min": 15984.0, "max": 32327.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2575180169011726, "min": -1.0000000521540642, "max": 1.4893937284359708, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 76.70859903097153, "min": -32.000001668930054, "max": 95.88499871641397, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2575180169011726, "min": -1.0000000521540642, "max": 1.4893937284359708, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 76.70859903097153, "min": -32.000001668930054, "max": 95.88499871641397, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04973049529400639, "min": 0.046205047617175816, "max": 9.239449052140117, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0335602129343897, "min": 3.0335602129343897, "max": 147.83118483424187, "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": "1722063057", "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": "1722065445" }, "total": 2388.872450245, "count": 1, "self": 0.9734802919997492, "children": { "run_training.setup": { "total": 0.06444327000002659, "count": 1, "self": 0.06444327000002659 }, "TrainerController.start_learning": { "total": 2387.834526683, "count": 1, "self": 1.8516109030083499, "children": { "TrainerController._reset_env": { "total": 3.112256306000006, "count": 1, "self": 3.112256306000006 }, "TrainerController.advance": { "total": 2382.7269239249918, "count": 63599, "self": 2.0515540609480922, "children": { "env_step": { "total": 1685.6943189220458, "count": 63599, "self": 1516.3934095910563, "children": { "SubprocessEnvManager._take_step": { "total": 168.1107849480208, "count": 63599, "self": 5.877355973048452, "children": { "TorchPolicy.evaluate": { "total": 162.23342897497236, "count": 62558, "self": 162.23342897497236 } } }, "workers": { "total": 1.1901243829685768, "count": 63599, "self": 0.0, "children": { "worker_root": { "total": 2381.386304543997, "count": 63599, "is_parallel": true, "self": 1020.5219337450271, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0076053220000176225, "count": 1, "is_parallel": true, "self": 0.005923467000002347, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016818550000152754, "count": 8, "is_parallel": true, "self": 0.0016818550000152754 } } }, "UnityEnvironment.step": { "total": 0.05479555699997718, "count": 1, "is_parallel": true, "self": 0.0007095229999549701, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005428549999919596, "count": 1, "is_parallel": true, "self": 0.0005428549999919596 }, "communicator.exchange": { "total": 0.05176948200005427, "count": 1, "is_parallel": true, "self": 0.05176948200005427 }, "steps_from_proto": { "total": 0.0017736969999759822, "count": 1, "is_parallel": true, "self": 0.00038195299987364706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013917440001023351, "count": 8, "is_parallel": true, "self": 0.0013917440001023351 } } } } } } }, "UnityEnvironment.step": { "total": 1360.86437079897, "count": 63598, "is_parallel": true, "self": 40.03084074593926, "children": { "UnityEnvironment._generate_step_input": { "total": 26.939076107988342, "count": 63598, "is_parallel": true, "self": 26.939076107988342 }, "communicator.exchange": { "total": 1177.9677646690336, "count": 63598, "is_parallel": true, "self": 1177.9677646690336 }, "steps_from_proto": { "total": 115.9266892760088, "count": 63598, "is_parallel": true, "self": 25.372031842967488, "children": { "_process_rank_one_or_two_observation": { "total": 90.55465743304131, "count": 508784, "is_parallel": true, "self": 90.55465743304131 } } } } } } } } } } }, "trainer_advance": { "total": 694.9810509419979, "count": 63599, "self": 3.6161587550302556, "children": { "process_trajectory": { "total": 143.01521473996314, "count": 63599, "self": 142.68410102796275, "children": { "RLTrainer._checkpoint": { "total": 0.33111371200038775, "count": 2, "self": 0.33111371200038775 } } }, "_update_policy": { "total": 548.3496774470045, "count": 447, "self": 326.6941437839842, "children": { "TorchPPOOptimizer.update": { "total": 221.65553366302032, "count": 22773, "self": 221.65553366302032 } } } } } } }, "trainer_threads": { "total": 1.4289998944150284e-06, "count": 1, "self": 1.4289998944150284e-06 }, "TrainerController._save_models": { "total": 0.1437341200003175, "count": 1, "self": 0.002053634000276361, "children": { "RLTrainer._checkpoint": { "total": 0.14168048600004113, "count": 1, "self": 0.14168048600004113 } } } } } } }