{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6055507659912109, "min": 0.5545971393585205, "max": 1.4652374982833862, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18079.32421875, "min": 16726.650390625, "max": 44449.4453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2062392234802246, "min": -0.12374486774206161, "max": 0.2062392234802246, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 52.59100341796875, "min": -29.327533721923828, "max": 52.59100341796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0064979721792042255, "min": 0.0064979721792042255, "max": 0.3841745853424072, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.6569828987121582, "min": 1.6569828987121582, "max": 91.04937744140625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06881269686208623, "min": 0.06485132826969102, "max": 0.07301852734026408, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0321904529312935, "min": 0.4856852018357999, "max": 1.065315728923808, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010306521416027357, "min": 0.00017163741776294076, "max": 0.010306521416027357, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15459782124041035, "min": 0.0022312864309182298, "max": 0.15459782124041035, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.514577495173328e-06, "min": 7.514577495173328e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011271866242759992, "min": 0.00011271866242759992, "max": 0.003374842075052699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250482666666665, "min": 0.10250482666666665, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375723999999997, "min": 1.3886848, "max": 2.4441297, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002602321839999998, "min": 0.0002602321839999998, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039034827599999967, "min": 0.0039034827599999967, "max": 0.11251223527000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009838652797043324, "min": 0.008644944988191128, "max": 0.3545594811439514, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14757978916168213, "min": 0.12102923542261124, "max": 2.4819164276123047, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 645.5744680851063, "min": 645.5744680851063, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30342.0, "min": 15984.0, "max": 32468.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8436297566649762, "min": -1.0000000521540642, "max": 0.8436297566649762, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 39.65059856325388, "min": -31.991201654076576, "max": 39.65059856325388, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8436297566649762, "min": -1.0000000521540642, "max": 0.8436297566649762, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 39.65059856325388, "min": -31.991201654076576, "max": 39.65059856325388, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06570717093950891, "min": 0.05926284129458034, "max": 7.321759932674468, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0882370341569185, "min": 2.7260906995506957, "max": 117.14815892279148, "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": "1741141852", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741143921" }, "total": 2069.5114491430004, "count": 1, "self": 0.4786240840012397, "children": { "run_training.setup": { "total": 0.020694608999747288, "count": 1, "self": 0.020694608999747288 }, "TrainerController.start_learning": { "total": 2069.0121304499994, "count": 1, "self": 1.30110292100062, "children": { "TrainerController._reset_env": { "total": 2.18894817599994, "count": 1, "self": 2.18894817599994 }, "TrainerController.advance": { "total": 2065.4370622749993, "count": 63363, "self": 1.407918851049999, "children": { "env_step": { "total": 1396.6957385759388, "count": 63363, "self": 1244.5475822899157, "children": { "SubprocessEnvManager._take_step": { "total": 151.3848700050039, "count": 63363, "self": 4.686394982047659, "children": { "TorchPolicy.evaluate": { "total": 146.69847502295625, "count": 62559, "self": 146.69847502295625 } } }, "workers": { "total": 0.7632862810191909, "count": 63363, "self": 0.0, "children": { "worker_root": { "total": 2064.1275298269557, "count": 63363, "is_parallel": true, "self": 929.5339436648378, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022362230001817807, "count": 1, "is_parallel": true, "self": 0.0007808270001987694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014553959999830113, "count": 8, "is_parallel": true, "self": 0.0014553959999830113 } } }, "UnityEnvironment.step": { "total": 0.04851416700012123, "count": 1, "is_parallel": true, "self": 0.0005423620004876284, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046651299999211915, "count": 1, "is_parallel": true, "self": 0.00046651299999211915 }, "communicator.exchange": { "total": 0.045957933999943634, "count": 1, "is_parallel": true, "self": 0.045957933999943634 }, "steps_from_proto": { "total": 0.0015473579996978515, "count": 1, "is_parallel": true, "self": 0.00033097199911935604, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012163860005784954, "count": 8, "is_parallel": true, "self": 0.0012163860005784954 } } } } } } }, "UnityEnvironment.step": { "total": 1134.5935861621178, "count": 63362, "is_parallel": true, "self": 31.249703146093907, "children": { "UnityEnvironment._generate_step_input": { "total": 23.086564969972187, "count": 63362, "is_parallel": true, "self": 23.086564969972187 }, "communicator.exchange": { "total": 984.4843640060108, "count": 63362, "is_parallel": true, "self": 984.4843640060108 }, "steps_from_proto": { "total": 95.77295404004099, "count": 63362, "is_parallel": true, "self": 19.25559823792628, "children": { "_process_rank_one_or_two_observation": { "total": 76.51735580211471, "count": 506896, "is_parallel": true, "self": 76.51735580211471 } } } } } } } } } } }, "trainer_advance": { "total": 667.3334048480106, "count": 63363, "self": 2.5397458720117356, "children": { "process_trajectory": { "total": 125.82038406499441, "count": 63363, "self": 125.61359581099441, "children": { "RLTrainer._checkpoint": { "total": 0.20678825400000278, "count": 2, "self": 0.20678825400000278 } } }, "_update_policy": { "total": 538.9732749110044, "count": 447, "self": 297.56945728405526, "children": { "TorchPPOOptimizer.update": { "total": 241.40381762694915, "count": 22740, "self": 241.40381762694915 } } } } } } }, "trainer_threads": { "total": 9.300001693191007e-07, "count": 1, "self": 9.300001693191007e-07 }, "TrainerController._save_models": { "total": 0.08501614799934032, "count": 1, "self": 0.0014787309992243536, "children": { "RLTrainer._checkpoint": { "total": 0.08353741700011597, "count": 1, "self": 0.08353741700011597 } } } } } } }