| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.3727378249168396, |
| "min": 0.3500407934188843, |
| "max": 1.448949933052063, |
| "count": 40 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 10991.29296875, |
| "min": 10568.431640625, |
| "max": 43955.34375, |
| "count": 40 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1199969.0, |
| "min": 29952.0, |
| "max": 1199969.0, |
| "count": 40 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1199969.0, |
| "min": 29952.0, |
| "max": 1199969.0, |
| "count": 40 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6842027306556702, |
| "min": -0.10395296663045883, |
| "max": 0.7050032615661621, |
| "count": 40 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 196.36618041992188, |
| "min": -24.948711395263672, |
| "max": 202.3359375, |
| "count": 40 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.021814122796058655, |
| "min": 0.004625443369150162, |
| "max": 0.22501064836978912, |
| "count": 40 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 6.260653495788574, |
| "min": 1.2673715353012085, |
| "max": 54.00255584716797, |
| "count": 40 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06820339822055152, |
| "min": 0.06575424749912206, |
| "max": 0.0728266060399446, |
| "count": 40 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9548475750877212, |
| "min": 0.4942122602719217, |
| "max": 1.0799974787137385, |
| "count": 40 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01770647350626643, |
| "min": 0.0001677883654474058, |
| "max": 0.01770647350626643, |
| "count": 40 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.24789062908773, |
| "min": 0.0020134603853688695, |
| "max": 0.26198252593918503, |
| "count": 40 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00018156871090568096, |
| "min": 0.00018156871090568096, |
| "max": 0.00029838354339596195, |
| "count": 40 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0025419619526795335, |
| "min": 0.0020886848037717336, |
| "max": 0.003927308090897333, |
| "count": 40 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.16052289047619048, |
| "min": 0.16052289047619048, |
| "max": 0.19946118095238097, |
| "count": 40 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 2.247320466666667, |
| "min": 1.3962282666666668, |
| "max": 2.7525654333333343, |
| "count": 40 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.006056236758571429, |
| "min": 0.006056236758571429, |
| "max": 0.009946171977142856, |
| "count": 40 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.08478731462000001, |
| "min": 0.06962320384, |
| "max": 0.13091935640000002, |
| "count": 40 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.008340010419487953, |
| "min": 0.008340010419487953, |
| "max": 0.3860357403755188, |
| "count": 40 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.11676014959812164, |
| "min": 0.11676014959812164, |
| "max": 2.7022502422332764, |
| "count": 40 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 258.87719298245617, |
| "min": 258.87719298245617, |
| "max": 999.0, |
| "count": 40 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29512.0, |
| "min": 15984.0, |
| "max": 32470.0, |
| "count": 40 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7420265284259762, |
| "min": -1.0000000521540642, |
| "max": 1.7420265284259762, |
| "count": 40 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 196.84899771213531, |
| "min": -31.998401671648026, |
| "max": 196.84899771213531, |
| "count": 40 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7420265284259762, |
| "min": -1.0000000521540642, |
| "max": 1.7420265284259762, |
| "count": 40 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 196.84899771213531, |
| "min": -31.998401671648026, |
| "max": 196.84899771213531, |
| "count": 40 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.022404033346081036, |
| "min": 0.022404033346081036, |
| "max": 7.82018069177866, |
| "count": 40 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.531655768107157, |
| "min": 2.531655768107157, |
| "max": 125.12289106845856, |
| "count": 40 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 40 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 40 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1677140563", |
| "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
| "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": "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": "1.22.4", |
| "end_time_seconds": "1677143258" |
| }, |
| "total": 2694.732394388, |
| "count": 1, |
| "self": 0.3392702930004816, |
| "children": { |
| "run_training.setup": { |
| "total": 0.10602526399998169, |
| "count": 1, |
| "self": 0.10602526399998169 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2694.2870988309996, |
| "count": 1, |
| "self": 1.6445071220905447, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 6.4523384210001495, |
| "count": 1, |
| "self": 6.4523384210001495 |
| }, |
| "TrainerController.advance": { |
| "total": 2686.048270196909, |
| "count": 77792, |
| "self": 1.7915910298170274, |
| "children": { |
| "env_step": { |
| "total": 1787.0869560109522, |
| "count": 77792, |
| "self": 1646.9183388157953, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 139.14214180304816, |
| "count": 77792, |
| "self": 5.741004645988596, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 133.40113715705957, |
| "count": 76061, |
| "self": 44.82925655898316, |
| "children": { |
| "TorchPolicy.sample_actions": { |
| "total": 88.5718805980764, |
| "count": 76061, |
| "self": 88.5718805980764 |
| } |
| } |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.0264753921087504, |
| "count": 77791, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2688.4260324488782, |
| "count": 77791, |
| "is_parallel": true, |
| "self": 1184.705385187906, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0019777120000981085, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007212129994513816, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001256499000646727, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001256499000646727 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.08285423999996055, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005538749996958359, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005083540004306997, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005083540004306997 |
| }, |
| "communicator.exchange": { |
| "total": 0.08002825999983543, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.08002825999983543 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017637509999985923, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004401500000312808, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013236009999673115, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013236009999673115 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1503.7206472609723, |
| "count": 77790, |
| "is_parallel": true, |
| "self": 37.4480420421437, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 28.668153776905456, |
| "count": 77790, |
| "is_parallel": true, |
| "self": 28.668153776905456 |
| }, |
| "communicator.exchange": { |
| "total": 1322.148492987008, |
| "count": 77790, |
| "is_parallel": true, |
| "self": 1322.148492987008 |
| }, |
| "steps_from_proto": { |
| "total": 115.45595845491516, |
| "count": 77790, |
| "is_parallel": true, |
| "self": 27.878334041896778, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 87.57762441301838, |
| "count": 622320, |
| "is_parallel": true, |
| "self": 87.57762441301838 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 897.1697231561398, |
| "count": 77791, |
| "self": 3.0829499581718665, |
| "children": { |
| "process_trajectory": { |
| "total": 199.4822866009572, |
| "count": 77791, |
| "self": 199.29614934395704, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.18613725700015493, |
| "count": 2, |
| "self": 0.18613725700015493 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 694.6044865970107, |
| "count": 549, |
| "self": 267.5196682960159, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 427.0848183009948, |
| "count": 27726, |
| "self": 427.0848183009948 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.3960006981506012e-06, |
| "count": 1, |
| "self": 1.3960006981506012e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.14198169499923097, |
| "count": 1, |
| "self": 0.0018931889999294071, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.14008850599930156, |
| "count": 1, |
| "self": 0.14008850599930156 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
