{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42247989773750305, "min": 0.2507127523422241, "max": 1.3387961387634277, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12525.68359375, "min": 7509.3486328125, "max": 40613.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08870507776737213, "min": -0.09990935772657394, "max": 0.1302768737077713, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.3779239654541, "min": -23.978246688842773, "max": 30.87561798095703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007405513897538185, "min": 0.007405513897538185, "max": 0.26140132546424866, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7847288846969604, "min": 1.7847288846969604, "max": 61.95211410522461, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0636985083229247, "min": 0.06222402359897639, "max": 0.08619558502930869, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8917791165209458, "min": 0.512270215733496, "max": 1.0180602577633644, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0011697235171670994, "min": 1.6828586770101862e-07, "max": 0.22390341937266836, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.01637612924033939, "min": 2.3560021478142606e-06, "max": 1.5673239356086786, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00024233366900523563, "min": 0.00024233366900523563, "max": 0.009838354287330745, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0033926713660732987, "min": 0.0033926713660732987, "max": 0.1001261503987385, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242333571428573, "min": 0.10242333571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339267000000002, "min": 1.327104, "max": 2.4012615000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002520912378571428, "min": 0.0002520912378571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035292773299999995, "min": 0.0035292773299999995, "max": 0.10016602384999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006938199978321791, "min": 0.006938199978321791, "max": 0.3823823928833008, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0971347987651825, "min": 0.0930439904332161, "max": 2.6766767501831055, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 942.0322580645161, "min": 877.8, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29203.0, "min": 15984.0, "max": 33136.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8136323096771394, "min": -1.0000000521540642, "max": -0.398328041434288, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -25.22260159999132, "min": -32.000001668930054, "max": -9.9582010358572, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8136323096771394, "min": -1.0000000521540642, "max": -0.398328041434288, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -25.22260159999132, "min": -32.000001668930054, "max": -9.9582010358572, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0704167797875632, "min": 0.0704167797875632, "max": 7.5239295568317175, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.182920173414459, "min": 2.182920173414459, "max": 120.38287290930748, "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": "1679764548", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679766642" }, "total": 2093.1895810589995, "count": 1, "self": 0.42674449300011474, "children": { "run_training.setup": { "total": 0.10148298900003283, "count": 1, "self": 0.10148298900003283 }, "TrainerController.start_learning": { "total": 2092.6613535769993, "count": 1, "self": 1.3110864339460022, "children": { "TrainerController._reset_env": { "total": 5.9665194620001785, "count": 1, "self": 5.9665194620001785 }, "TrainerController.advance": { "total": 2085.2885122760536, "count": 63002, "self": 1.4301724810857195, "children": { "env_step": { "total": 1462.7712967929701, "count": 63002, "self": 1354.7328569310566, "children": { "SubprocessEnvManager._take_step": { "total": 107.19787674897725, "count": 63002, "self": 4.6925786661495295, "children": { "TorchPolicy.evaluate": { "total": 102.50529808282772, "count": 62564, "self": 102.50529808282772 } } }, "workers": { "total": 0.8405631129362519, "count": 63002, "self": 0.0, "children": { "worker_root": { "total": 2087.9617663450654, "count": 63002, "is_parallel": true, "self": 846.8736037550943, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018512480000936193, "count": 1, "is_parallel": true, "self": 0.0005588340009126114, "children": { "_process_rank_one_or_two_observation": { "total": 0.001292413999181008, "count": 8, "is_parallel": true, "self": 0.001292413999181008 } } }, "UnityEnvironment.step": { "total": 0.04606646699994599, "count": 1, "is_parallel": true, "self": 0.0005352190000849077, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048139899990928825, "count": 1, "is_parallel": true, "self": 0.00048139899990928825 }, "communicator.exchange": { "total": 0.04313178199936374, "count": 1, "is_parallel": true, "self": 0.04313178199936374 }, "steps_from_proto": { "total": 0.001918067000588053, "count": 1, "is_parallel": true, "self": 0.00044711300142807886, "children": { "_process_rank_one_or_two_observation": { "total": 0.001470953999159974, "count": 8, "is_parallel": true, "self": 0.001470953999159974 } } } } } } }, "UnityEnvironment.step": { "total": 1241.088162589971, "count": 63001, "is_parallel": true, "self": 30.465440786872932, "children": { "UnityEnvironment._generate_step_input": { "total": 22.175739983982567, "count": 63001, "is_parallel": true, "self": 22.175739983982567 }, "communicator.exchange": { "total": 1097.9550138070117, "count": 63001, "is_parallel": true, "self": 1097.9550138070117 }, "steps_from_proto": { "total": 90.49196801210383, "count": 63001, "is_parallel": true, "self": 19.16001759790288, "children": { "_process_rank_one_or_two_observation": { "total": 71.33195041420095, "count": 504008, "is_parallel": true, "self": 71.33195041420095 } } } } } } } } } } }, "trainer_advance": { "total": 621.0870430019977, "count": 63002, "self": 2.3550194468389236, "children": { "process_trajectory": { "total": 111.27673798415708, "count": 63002, "self": 111.08167639015664, "children": { "RLTrainer._checkpoint": { "total": 0.19506159400043543, "count": 2, "self": 0.19506159400043543 } } }, "_update_policy": { "total": 507.4552855710017, "count": 420, "self": 322.4564692430504, "children": { "TorchPPOOptimizer.update": { "total": 184.99881632795132, "count": 22806, "self": 184.99881632795132 } } } } } } }, "trainer_threads": { "total": 9.980003596865572e-07, "count": 1, "self": 9.980003596865572e-07 }, "TrainerController._save_models": { "total": 0.09523440699922503, "count": 1, "self": 0.001514858999144053, "children": { "RLTrainer._checkpoint": { "total": 0.09371954800008098, "count": 1, "self": 0.09371954800008098 } } } } } } }