{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40421146154403687, "min": 0.3900611400604248, "max": 1.4220385551452637, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12229.822265625, "min": 11832.89453125, "max": 43138.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45397019386291504, "min": -0.09806715697050095, "max": 0.45397019386291504, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.11798095703125, "min": -23.536117553710938, "max": 122.11798095703125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03029509261250496, "min": 0.012826653197407722, "max": 0.37066441774368286, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.14937973022461, "min": 3.3477563858032227, "max": 89.70079040527344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0646145743251379, "min": 0.06449364745778786, "max": 0.07379282712229808, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9046040405519306, "min": 0.4906740198552478, "max": 1.0362290481342844, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014095034164451395, "min": 0.0011287499840143447, "max": 0.014734205211476387, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19733047830231953, "min": 0.013544999808172137, "max": 0.21031653406994424, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.736625992585715e-06, "min": 7.736625992585715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010831276389620001, "min": 0.00010831276389620001, "max": 0.0037586017471328, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257884285714287, "min": 0.10257884285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361038000000002, "min": 1.3886848, "max": 2.6528672, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026762640142857157, "min": 0.00026762640142857157, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003746769620000002, "min": 0.003746769620000002, "max": 0.12530143327999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01127512939274311, "min": 0.01127512939274311, "max": 0.5623432397842407, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15785181522369385, "min": 0.15785181522369385, "max": 3.9364025592803955, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 396.8333333333333, "min": 396.8333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28572.0, "min": 15984.0, "max": 32609.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4642249792814255, "min": -1.0000000521540642, "max": 1.4642249792814255, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.42419850826263, "min": -28.59200168401003, "max": 105.42419850826263, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4642249792814255, "min": -1.0000000521540642, "max": 1.4642249792814255, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.42419850826263, "min": -28.59200168401003, "max": 105.42419850826263, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04601876299622947, "min": 0.04601876299622947, "max": 10.807187784463167, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.313350935728522, "min": 3.313350935728522, "max": 172.91500455141068, "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": "1709818948", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709821087" }, "total": 2139.025751825, "count": 1, "self": 0.48922855899945716, "children": { "run_training.setup": { "total": 0.07241502400006539, "count": 1, "self": 0.07241502400006539 }, "TrainerController.start_learning": { "total": 2138.4641082420003, "count": 1, "self": 1.4201732789338166, "children": { "TrainerController._reset_env": { "total": 2.7074063380000553, "count": 1, "self": 2.7074063380000553 }, "TrainerController.advance": { "total": 2134.249281587067, "count": 63716, "self": 1.4183746530584358, "children": { "env_step": { "total": 1503.2300916709958, "count": 63716, "self": 1370.6750627439774, "children": { "SubprocessEnvManager._take_step": { "total": 131.71663118400556, "count": 63716, "self": 4.750618732021394, "children": { "TorchPolicy.evaluate": { "total": 126.96601245198417, "count": 62556, "self": 126.96601245198417 } } }, "workers": { "total": 0.8383977430128198, "count": 63716, "self": 0.0, "children": { "worker_root": { "total": 2133.407904239973, "count": 63716, "is_parallel": true, "self": 883.2150442549532, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003378153000085149, "count": 1, "is_parallel": true, "self": 0.0007955710000260297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025825820000591193, "count": 8, "is_parallel": true, "self": 0.0025825820000591193 } } }, "UnityEnvironment.step": { "total": 0.054230354000083025, "count": 1, "is_parallel": true, "self": 0.0006506530000933708, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047547899998789944, "count": 1, "is_parallel": true, "self": 0.00047547899998789944 }, "communicator.exchange": { "total": 0.051361457999973936, "count": 1, "is_parallel": true, "self": 0.051361457999973936 }, "steps_from_proto": { "total": 0.0017427640000278188, "count": 1, "is_parallel": true, "self": 0.00037689500004489673, "children": { "_process_rank_one_or_two_observation": { "total": 0.001365868999982922, "count": 8, "is_parallel": true, "self": 0.001365868999982922 } } } } } } }, "UnityEnvironment.step": { "total": 1250.1928599850198, "count": 63715, "is_parallel": true, "self": 34.54860331109671, "children": { "UnityEnvironment._generate_step_input": { "total": 23.683440513997994, "count": 63715, "is_parallel": true, "self": 23.683440513997994 }, "communicator.exchange": { "total": 1092.4503276479088, "count": 63715, "is_parallel": true, "self": 1092.4503276479088 }, "steps_from_proto": { "total": 99.51048851201631, "count": 63715, "is_parallel": true, "self": 19.92456077600309, "children": { "_process_rank_one_or_two_observation": { "total": 79.58592773601322, "count": 509720, "is_parallel": true, "self": 79.58592773601322 } } } } } } } } } } }, "trainer_advance": { "total": 629.6008152630125, "count": 63716, "self": 2.7628627929852883, "children": { "process_trajectory": { "total": 128.62663711702317, "count": 63716, "self": 128.42107384102292, "children": { "RLTrainer._checkpoint": { "total": 0.20556327600024815, "count": 2, "self": 0.20556327600024815 } } }, "_update_policy": { "total": 498.211315353004, "count": 456, "self": 289.40749924605393, "children": { "TorchPPOOptimizer.update": { "total": 208.80381610695008, "count": 22800, "self": 208.80381610695008 } } } } } } }, "trainer_threads": { "total": 9.649997991800774e-07, "count": 1, "self": 9.649997991800774e-07 }, "TrainerController._save_models": { "total": 0.08724607299973286, "count": 1, "self": 0.0013949629997114243, "children": { "RLTrainer._checkpoint": { "total": 0.08585111000002144, "count": 1, "self": 0.08585111000002144 } } } } } } }