{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35387760400772095, "min": 0.35387760400772095, "max": 1.4217941761016846, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10661.6240234375, "min": 10661.6240234375, "max": 43131.546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.615755558013916, "min": -0.14204280078411102, "max": 0.6987961530685425, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 173.02731323242188, "min": -34.23231506347656, "max": 201.2532958984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005153913516551256, "min": -0.006782663054764271, "max": 0.5042229294776917, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4482496976852417, "min": -1.9466242790222168, "max": 119.5008316040039, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06864598624746404, "min": 0.06388031195204717, "max": 0.07324197360463837, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9610438074644966, "min": 0.4808233019470333, "max": 1.044971257460751, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01658858748782049, "min": 0.001348460036721806, "max": 0.01692406725764851, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23224022482948686, "min": 0.013484600367218061, "max": 0.23693694160707915, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.281119001564285e-06, "min": 7.281119001564285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010193566602189999, "min": 0.00010193566602189999, "max": 0.0035075327308224996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242700714285714, "min": 0.10242700714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339781, "min": 1.3886848, "max": 2.5691775000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025245801357142865, "min": 0.00025245801357142865, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035344121900000008, "min": 0.0035344121900000008, "max": 0.11694083225000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011550010181963444, "min": 0.011442795395851135, "max": 0.6414904594421387, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16170014441013336, "min": 0.16170014441013336, "max": 4.490433216094971, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 321.6868686868687, "min": 277.14953271028037, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31847.0, "min": 15984.0, "max": 33289.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6362509997371508, "min": -1.0000000521540642, "max": 1.7228504523774173, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 160.35259797424078, "min": -30.725001737475395, "max": 184.34499840438366, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6362509997371508, "min": -1.0000000521540642, "max": 1.7228504523774173, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 160.35259797424078, "min": -30.725001737475395, "max": 184.34499840438366, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0377721007633004, "min": 0.03290370552842484, "max": 13.744561335071921, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.701665874803439, "min": 3.43801405481463, "max": 219.91298136115074, "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": "1685588850", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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=Pyramids1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685591033" }, "total": 2182.865025009, "count": 1, "self": 0.897818591000032, "children": { "run_training.setup": { "total": 0.05803418400000737, "count": 1, "self": 0.05803418400000737 }, "TrainerController.start_learning": { "total": 2181.909172234, "count": 1, "self": 1.3171307559878187, "children": { "TrainerController._reset_env": { "total": 4.0835039329999745, "count": 1, "self": 4.0835039329999745 }, "TrainerController.advance": { "total": 2176.360063110012, "count": 63937, "self": 1.267298906015185, "children": { "env_step": { "total": 1539.8548130000295, "count": 63937, "self": 1433.8517908360172, "children": { "SubprocessEnvManager._take_step": { "total": 105.25777354203547, "count": 63937, "self": 4.582564628095497, "children": { "TorchPolicy.evaluate": { "total": 100.67520891393997, "count": 62551, "self": 100.67520891393997 } } }, "workers": { "total": 0.7452486219767707, "count": 63937, "self": 0.0, "children": { "worker_root": { "total": 2176.873523509887, "count": 63937, "is_parallel": true, "self": 851.8711737788044, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001781079000011232, "count": 1, "is_parallel": true, "self": 0.0005481289995259431, "children": { "_process_rank_one_or_two_observation": { "total": 0.001232950000485289, "count": 8, "is_parallel": true, "self": 0.001232950000485289 } } }, "UnityEnvironment.step": { "total": 0.05124231800027701, "count": 1, "is_parallel": true, "self": 0.0005895570002394379, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004731389999506064, "count": 1, "is_parallel": true, "self": 0.0004731389999506064 }, "communicator.exchange": { "total": 0.04835131600020759, "count": 1, "is_parallel": true, "self": 0.04835131600020759 }, "steps_from_proto": { "total": 0.001828305999879376, "count": 1, "is_parallel": true, "self": 0.00034735899998850073, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014809469998908753, "count": 8, "is_parallel": true, "self": 0.0014809469998908753 } } } } } } }, "UnityEnvironment.step": { "total": 1325.0023497310826, "count": 63936, "is_parallel": true, "self": 33.198003245239306, "children": { "UnityEnvironment._generate_step_input": { "total": 22.7005301160234, "count": 63936, "is_parallel": true, "self": 22.7005301160234 }, "communicator.exchange": { "total": 1169.1600615759367, "count": 63936, "is_parallel": true, "self": 1169.1600615759367 }, "steps_from_proto": { "total": 99.94375479388327, "count": 63936, "is_parallel": true, "self": 19.585495869819624, "children": { "_process_rank_one_or_two_observation": { "total": 80.35825892406365, "count": 511488, "is_parallel": true, "self": 80.35825892406365 } } } } } } } } } } }, "trainer_advance": { "total": 635.2379512039674, "count": 63937, "self": 2.4846043049788022, "children": { "process_trajectory": { "total": 106.54655229298805, "count": 63937, "self": 106.28988313898753, "children": { "RLTrainer._checkpoint": { "total": 0.2566691540005195, "count": 2, "self": 0.2566691540005195 } } }, "_update_policy": { "total": 526.2067946060006, "count": 450, "self": 336.9908844689994, "children": { "TorchPPOOptimizer.update": { "total": 189.21591013700117, "count": 22809, "self": 189.21591013700117 } } } } } } }, "trainer_threads": { "total": 1.4550005289493129e-06, "count": 1, "self": 1.4550005289493129e-06 }, "TrainerController._save_models": { "total": 0.1484729799994966, "count": 1, "self": 0.0018286019994775415, "children": { "RLTrainer._checkpoint": { "total": 0.14664437800001906, "count": 1, "self": 0.14664437800001906 } } } } } } }