{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15806080400943756, "min": 0.13881325721740723, "max": 1.4173345565795898, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4686.1865234375, "min": 4155.513671875, "max": 42996.26171875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999940.0, "min": 29997.0, "max": 2999940.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999940.0, "min": 29997.0, "max": 2999940.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6848976016044617, "min": -0.08549786359071732, "max": 0.8862026333808899, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 198.62030029296875, "min": -20.604984283447266, "max": 272.9504089355469, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0033752787858247757, "min": -0.07173072546720505, "max": 0.44486451148986816, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.978830873966217, "min": -20.228065490722656, "max": 105.87775421142578, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06753332911189534, "min": 0.06367647686385594, "max": 0.07467995852677992, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9454666075665349, "min": 0.5974396682142393, "max": 1.0798698961700535, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016840052705014215, "min": 0.0012196045591119687, "max": 0.017467749663046556, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.235760737870199, "min": 0.014635254709343626, "max": 0.26201624494569836, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4764709364476196e-06, "min": 1.4764709364476196e-06, "max": 0.0002982831130722958, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0670593110266674e-05, "min": 2.0670593110266674e-05, "max": 0.003926410491196534, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049212380952381, "min": 0.10049212380952381, "max": 0.1994277041666667, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068897333333334, "min": 1.4068897333333334, "max": 2.7375264333333336, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9163168571428595e-05, "min": 5.9163168571428595e-05, "max": 0.00994282764625, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008282843600000003, "min": 0.0008282843600000003, "max": 0.13088946631999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007082557771354914, "min": 0.006573705933988094, "max": 0.5421992540359497, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09915580600500107, "min": 0.09203188121318817, "max": 4.337594032287598, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 244.364406779661, "min": 222.17037037037036, "max": 986.060606060606, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28835.0, "min": 16284.0, "max": 33562.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6883209877404846, "min": -0.9263515641743486, "max": 1.777829615937339, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 200.91019754111767, "min": -30.569601617753506, "max": 240.00699815154076, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6883209877404846, "min": -0.9263515641743486, "max": 1.777829615937339, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 200.91019754111767, "min": -30.569601617753506, "max": 240.00699815154076, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017988570448805523, "min": 0.01715568055806216, "max": 11.286306420669836, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1406398834078573, "min": 1.9901636108616003, "max": 191.86720915138721, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673380634", "python_version": "3.8.16+ (heads/3.8-dirty:266a502edf, Jan 10 2023, 19:44:43) \n[GCC 7.5.0]", "command_line_arguments": "/home/micha/notes/topics/rl/ml-agents/venv/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": "1.19.3", "end_time_seconds": "1673393359" }, "total": 12725.26021479629, "count": 1, "self": 0.3219818873330951, "children": { "run_training.setup": { "total": 0.012263622134923935, "count": 1, "self": 0.012263622134923935 }, "TrainerController.start_learning": { "total": 12724.925969286822, "count": 1, "self": 4.676108851097524, "children": { "TrainerController._reset_env": { "total": 5.681364719755948, "count": 1, "self": 5.681364719755948 }, "TrainerController.advance": { "total": 12714.477960832417, "count": 194753, "self": 4.439157129265368, "children": { "env_step": { "total": 6338.861052524298, "count": 194753, "self": 3234.9188879150897, "children": { "SubprocessEnvManager._take_step": { "total": 3101.076901695691, "count": 194753, "self": 14.49980294983834, "children": { "TorchPolicy.evaluate": { "total": 3086.5770987458527, "count": 187551, "self": 2361.0189430397004, "children": { "TorchPolicy.sample_actions": { "total": 725.5581557061523, "count": 187551, "self": 725.5581557061523 } } } } }, "workers": { "total": 2.865262913517654, "count": 194753, "self": 0.0, "children": { "worker_root": { "total": 12717.946939884685, "count": 194753, "is_parallel": true, "self": 9804.73804064095, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019322065636515617, "count": 1, "is_parallel": true, "self": 0.00045424699783325195, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014779595658183098, "count": 8, "is_parallel": true, "self": 0.0014779595658183098 } } }, "UnityEnvironment.step": { "total": 0.03020785842090845, "count": 1, "is_parallel": true, "self": 0.0003406377509236336, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034890323877334595, "count": 1, "is_parallel": true, "self": 0.00034890323877334595 }, "communicator.exchange": { "total": 0.02810798678547144, "count": 1, "is_parallel": true, "self": 0.02810798678547144 }, "steps_from_proto": { "total": 0.0014103306457400322, "count": 1, "is_parallel": true, "self": 0.00024128146469593048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011690491810441017, "count": 8, "is_parallel": true, "self": 0.0011690491810441017 } } } } } } }, "UnityEnvironment.step": { "total": 2913.208899243735, "count": 194752, "is_parallel": true, "self": 64.70640704873949, "children": { "UnityEnvironment._generate_step_input": { "total": 49.73187546618283, "count": 194752, "is_parallel": true, "self": 49.73187546618283 }, "communicator.exchange": { "total": 2528.2268620384857, "count": 194752, "is_parallel": true, "self": 2528.2268620384857 }, "steps_from_proto": { "total": 270.54375469032675, "count": 194752, "is_parallel": true, "self": 42.92158390302211, "children": { "_process_rank_one_or_two_observation": { "total": 227.62217078730464, "count": 1558016, "is_parallel": true, "self": 227.62217078730464 } } } } } } } } } } }, "trainer_advance": { "total": 6371.177751178853, "count": 194753, "self": 9.854547733440995, "children": { "process_trajectory": { "total": 1708.413050682284, "count": 194753, "self": 1707.8554912619293, "children": { "RLTrainer._checkpoint": { "total": 0.5575594203546643, "count": 6, "self": 0.5575594203546643 } } }, "_update_policy": { "total": 4652.910152763128, "count": 1402, "self": 787.0403881333768, "children": { "TorchPPOOptimizer.update": { "total": 3865.8697646297514, "count": 68367, "self": 3865.8697646297514 } } } } } } }, "trainer_threads": { "total": 1.2237578630447388e-06, "count": 1, "self": 1.2237578630447388e-06 }, "TrainerController._save_models": { "total": 0.09053365979343653, "count": 1, "self": 0.0014272220432758331, "children": { "RLTrainer._checkpoint": { "total": 0.0891064377501607, "count": 1, "self": 0.0891064377501607 } } } } } } }