{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39538851380348206, "min": 0.39538851380348206, "max": 1.38942289352417, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11886.9599609375, "min": 11886.9599609375, "max": 42149.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29967.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29967.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.29764261841773987, "min": -0.11905121803283691, "max": 0.29764261841773987, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 77.68472290039062, "min": -28.57229232788086, "max": 77.68472290039062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 5.049723148345947, "min": 0.002880493411794305, "max": 5.153602600097656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1317.977783203125, "min": 0.7431672811508179, "max": 1355.3974609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06850021007638941, "min": 0.06512325192171968, "max": 0.0729450000784924, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0275031511458412, "min": 0.5106150005494469, "max": 1.0803411733130832, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 3.3813713929305473, "min": 0.00016139952568518872, "max": 4.183481407484838, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 50.72057089395821, "min": 0.0020981938339074534, "max": 58.56873970478773, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.483497505533335e-06, "min": 7.483497505533335e-06, "max": 0.00029523775873027143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011225246258300003, "min": 0.00011225246258300003, "max": 0.003373588075470699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249446666666669, "min": 0.10249446666666669, "max": 0.19841258571428572, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374170000000003, "min": 1.3888881, "max": 2.4853981000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025919722000000017, "min": 0.00025919722000000017, "max": 0.009841417312857143, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038879583000000022, "min": 0.0038879583000000022, "max": 0.11247047707000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01441147830337286, "min": 0.01441147830337286, "max": 0.4470309913158417, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21617217361927032, "min": 0.21094852685928345, "max": 3.1292169094085693, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 511.1929824561403, "min": 490.28846153846155, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29138.0, "min": 16638.0, "max": 34305.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2080350608417862, "min": -0.9998903750411926, "max": 1.2403961268181984, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 68.85799846798182, "min": -30.99660162627697, "max": 68.85799846798182, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2080350608417862, "min": -0.9998903750411926, "max": 1.2403961268181984, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 68.85799846798182, "min": -30.99660162627697, "max": 68.85799846798182, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07679309136501775, "min": 0.07679309136501775, "max": 8.521745932891088, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.377206207806012, "min": 4.3321405061287805, "max": 144.8696808591485, "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": "1710127277", "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": "1710129428" }, "total": 2150.9964587529994, "count": 1, "self": 0.526970311999321, "children": { "run_training.setup": { "total": 0.0550429670001904, "count": 1, "self": 0.0550429670001904 }, "TrainerController.start_learning": { "total": 2150.414445474, "count": 1, "self": 1.4685370589786544, "children": { "TrainerController._reset_env": { "total": 2.300935348999701, "count": 1, "self": 2.300935348999701 }, "TrainerController.advance": { "total": 2146.558735994022, "count": 63330, "self": 1.6334185090945539, "children": { "env_step": { "total": 1492.460517768015, "count": 63330, "self": 1350.3190028890294, "children": { "SubprocessEnvManager._take_step": { "total": 141.2464325449546, "count": 63330, "self": 4.982179163030196, "children": { "TorchPolicy.evaluate": { "total": 136.2642533819244, "count": 62560, "self": 136.2642533819244 } } }, "workers": { "total": 0.8950823340310308, "count": 63330, "self": 0.0, "children": { "worker_root": { "total": 2145.1393446600678, "count": 63330, "is_parallel": true, "self": 920.2877215810158, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023770010002408526, "count": 1, "is_parallel": true, "self": 0.0006949399994482519, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016820610007926007, "count": 8, "is_parallel": true, "self": 0.0016820610007926007 } } }, "UnityEnvironment.step": { "total": 0.05349537399979454, "count": 1, "is_parallel": true, "self": 0.0006773929990231409, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004554840006676386, "count": 1, "is_parallel": true, "self": 0.0004554840006676386 }, "communicator.exchange": { "total": 0.05060221100029594, "count": 1, "is_parallel": true, "self": 0.05060221100029594 }, "steps_from_proto": { "total": 0.0017602859998078202, "count": 1, "is_parallel": true, "self": 0.0003565399974831962, "children": { "_process_rank_one_or_two_observation": { "total": 0.001403746002324624, "count": 8, "is_parallel": true, "self": 0.001403746002324624 } } } } } } }, "UnityEnvironment.step": { "total": 1224.851623079052, "count": 63329, "is_parallel": true, "self": 36.525143415653474, "children": { "UnityEnvironment._generate_step_input": { "total": 24.41397602021334, "count": 63329, "is_parallel": true, "self": 24.41397602021334 }, "communicator.exchange": { "total": 1059.491220503107, "count": 63329, "is_parallel": true, "self": 1059.491220503107 }, "steps_from_proto": { "total": 104.42128314007823, "count": 63329, "is_parallel": true, "self": 21.256275652786826, "children": { "_process_rank_one_or_two_observation": { "total": 83.1650074872914, "count": 506632, "is_parallel": true, "self": 83.1650074872914 } } } } } } } } } } }, "trainer_advance": { "total": 652.4647997169122, "count": 63330, "self": 2.8916773018354434, "children": { "process_trajectory": { "total": 129.07337028508482, "count": 63330, "self": 128.86787921508403, "children": { "RLTrainer._checkpoint": { "total": 0.20549107000078948, "count": 2, "self": 0.20549107000078948 } } }, "_update_policy": { "total": 520.499752129992, "count": 451, "self": 304.97874450604286, "children": { "TorchPPOOptimizer.update": { "total": 215.52100762394912, "count": 22803, "self": 215.52100762394912 } } } } } } }, "trainer_threads": { "total": 8.589995559304953e-07, "count": 1, "self": 8.589995559304953e-07 }, "TrainerController._save_models": { "total": 0.08623621300012019, "count": 1, "self": 0.0014567629996236064, "children": { "RLTrainer._checkpoint": { "total": 0.08477945000049658, "count": 1, "self": 0.08477945000049658 } } } } } } }