{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43960413336753845, "min": 0.43960413336753845, "max": 1.4610804319381714, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13110.75390625, "min": 13110.75390625, "max": 44323.3359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989959.0, "min": 29952.0, "max": 989959.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989959.0, "min": 29952.0, "max": 989959.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5806640386581421, "min": -0.09016567468643188, "max": 0.6543744802474976, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 163.74725341796875, "min": -21.72992706298828, "max": 184.53359985351562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008783583529293537, "min": 0.0017583086155354977, "max": 0.3033042252063751, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.476970672607422, "min": 0.48177656531333923, "max": 71.88310241699219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0690520154448397, "min": 0.06512316297909312, "max": 0.07517845027524139, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9667282162277557, "min": 0.49706825048926334, "max": 1.03948307893748, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015597733926759769, "min": 0.0006896376812282005, "max": 0.01724620576521071, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21836827497463676, "min": 0.009654927537194807, "max": 0.2586930864781607, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.616840318228567e-06, "min": 7.616840318228567e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010663576445519995, "min": 0.00010663576445519995, "max": 0.0036342937885687995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025389142857143, "min": 0.1025389142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355448000000002, "min": 1.3886848, "max": 2.6114311999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002636375371428571, "min": 0.0002636375371428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036909255199999995, "min": 0.0036909255199999995, "max": 0.12116197688000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011125159449875355, "min": 0.011125159449875355, "max": 0.3486703038215637, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15575222671031952, "min": 0.15575222671031952, "max": 2.440692186355591, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 325.8510638297872, "min": 291.4950495049505, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30630.0, "min": 15984.0, "max": 34179.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5890212580561638, "min": -1.0000000521540642, "max": 1.708504937958009, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.3679982572794, "min": -29.519401639699936, "max": 172.55899873375893, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5890212580561638, "min": -1.0000000521540642, "max": 1.708504937958009, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.3679982572794, "min": -29.519401639699936, "max": 172.55899873375893, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.037652126635409934, "min": 0.034524055748502494, "max": 6.665480062365532, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5392999037285335, "min": 3.472035982122179, "max": 106.64768099784851, "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": "1709106716", "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": "1709108987" }, "total": 2271.301147620001, "count": 1, "self": 0.47770029000184877, "children": { "run_training.setup": { "total": 0.049757023999518424, "count": 1, "self": 0.049757023999518424 }, "TrainerController.start_learning": { "total": 2270.7736903059995, "count": 1, "self": 1.6577021178554787, "children": { "TrainerController._reset_env": { "total": 2.468708563000291, "count": 1, "self": 2.468708563000291 }, "TrainerController.advance": { "total": 2266.5616141931423, "count": 63860, "self": 1.5924560190214834, "children": { "env_step": { "total": 1623.1308687120463, "count": 63860, "self": 1482.5782351961416, "children": { "SubprocessEnvManager._take_step": { "total": 139.56849276592948, "count": 63860, "self": 5.0331046189185145, "children": { "TorchPolicy.evaluate": { "total": 134.53538814701096, "count": 62559, "self": 134.53538814701096 } } }, "workers": { "total": 0.9841407499752677, "count": 63860, "self": 0.0, "children": { "worker_root": { "total": 2264.804816413919, "count": 63860, "is_parallel": true, "self": 906.6696877678751, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001991301999623829, "count": 1, "is_parallel": true, "self": 0.0006277259990383754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013635760005854536, "count": 8, "is_parallel": true, "self": 0.0013635760005854536 } } }, "UnityEnvironment.step": { "total": 0.04723054099940782, "count": 1, "is_parallel": true, "self": 0.0005804549991808017, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044976100070925895, "count": 1, "is_parallel": true, "self": 0.00044976100070925895 }, "communicator.exchange": { "total": 0.04441687999951682, "count": 1, "is_parallel": true, "self": 0.04441687999951682 }, "steps_from_proto": { "total": 0.0017834450000009383, "count": 1, "is_parallel": true, "self": 0.000422005998188979, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013614390018119593, "count": 8, "is_parallel": true, "self": 0.0013614390018119593 } } } } } } }, "UnityEnvironment.step": { "total": 1358.135128646044, "count": 63859, "is_parallel": true, "self": 36.31733745216752, "children": { "UnityEnvironment._generate_step_input": { "total": 24.341690778076554, "count": 63859, "is_parallel": true, "self": 24.341690778076554 }, "communicator.exchange": { "total": 1194.6360555799392, "count": 63859, "is_parallel": true, "self": 1194.6360555799392 }, "steps_from_proto": { "total": 102.84004483586068, "count": 63859, "is_parallel": true, "self": 21.191354453668282, "children": { "_process_rank_one_or_two_observation": { "total": 81.6486903821924, "count": 510872, "is_parallel": true, "self": 81.6486903821924 } } } } } } } } } } }, "trainer_advance": { "total": 641.8382894620745, "count": 63860, "self": 3.1867888792558006, "children": { "process_trajectory": { "total": 130.08793731981496, "count": 63860, "self": 129.87970483781373, "children": { "RLTrainer._checkpoint": { "total": 0.2082324820012218, "count": 2, "self": 0.2082324820012218 } } }, "_update_policy": { "total": 508.56356326300374, "count": 455, "self": 297.3762884029693, "children": { "TorchPPOOptimizer.update": { "total": 211.18727486003445, "count": 22749, "self": 211.18727486003445 } } } } } } }, "trainer_threads": { "total": 1.272001100005582e-06, "count": 1, "self": 1.272001100005582e-06 }, "TrainerController._save_models": { "total": 0.08566416000030586, "count": 1, "self": 0.0014741560007678345, "children": { "RLTrainer._checkpoint": { "total": 0.08419000399953802, "count": 1, "self": 0.08419000399953802 } } } } } } }