{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2840893864631653, "min": 0.2796804904937744, "max": 1.270157814025879, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8459.0458984375, "min": 8314.341796875, "max": 38531.5078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989959.0, "min": 29958.0, "max": 989959.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989959.0, "min": 29958.0, "max": 989959.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5700079202651978, "min": -0.12232279032468796, "max": 0.6135962605476379, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.89219665527344, "min": -29.602115631103516, "max": 173.03414916992188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020416734740138054, "min": -0.0839371606707573, "max": 0.5024430155754089, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.655435562133789, "min": -22.495159149169922, "max": 120.5863265991211, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07035438934066666, "min": 0.06475634997505474, "max": 0.07252574436815264, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9849614507693333, "min": 0.5560768469438845, "max": 1.0678913174082945, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013174142023975339, "min": 0.0007342734590907243, "max": 0.02038204197392536, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18443798833565475, "min": 0.009545554968179416, "max": 0.2552109110498956, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3897189653642875e-06, "min": 7.3897189653642875e-06, "max": 0.00029477253924248747, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010345606551510003, "min": 0.00010345606551510003, "max": 0.0033759772746743, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246320714285716, "min": 0.10246320714285716, "max": 0.1982575125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344849000000002, "min": 1.4344849000000002, "max": 2.4442364999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002560743935714286, "min": 0.0002560743935714286, "max": 0.009825925498749999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035850415100000007, "min": 0.0035850415100000007, "max": 0.11255003743000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.040937427431344986, "min": 0.040937427431344986, "max": 0.6928895115852356, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.5731239914894104, "min": 0.5731239914894104, "max": 5.543116092681885, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 320.3333333333333, "min": 320.3333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28830.0, "min": 17140.0, "max": 32466.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6352110852797825, "min": -0.9999250518158078, "max": 1.6352110852797825, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.16899767518044, "min": -31.99760165810585, "max": 154.74219779670238, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6352110852797825, "min": -0.9999250518158078, "max": 1.6352110852797825, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.16899767518044, "min": -31.99760165810585, "max": 154.74219779670238, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.13109392847076784, "min": 0.13109392847076784, "max": 13.051823073480692, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 11.798453562369104, "min": 11.798453562369104, "max": 234.93281532265246, "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": "1674134582", "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": "1.21.6", "end_time_seconds": "1674136573" }, "total": 1991.0610932460002, "count": 1, "self": 0.4825284449998435, "children": { "run_training.setup": { "total": 0.10515970000000152, "count": 1, "self": 0.10515970000000152 }, "TrainerController.start_learning": { "total": 1990.4734051010003, "count": 1, "self": 1.207794748022252, "children": { "TrainerController._reset_env": { "total": 9.672737317999974, "count": 1, "self": 9.672737317999974 }, "TrainerController.advance": { "total": 1979.507767463978, "count": 63912, "self": 1.235416421931177, "children": { "env_step": { "total": 1348.456016733053, "count": 63912, "self": 1246.1980871520752, "children": { "SubprocessEnvManager._take_step": { "total": 101.50528131100145, "count": 63912, "self": 4.306715628998745, "children": { "TorchPolicy.evaluate": { "total": 97.19856568200271, "count": 62537, "self": 32.73524385000724, "children": { "TorchPolicy.sample_actions": { "total": 64.46332183199547, "count": 62537, "self": 64.46332183199547 } } } } }, "workers": { "total": 0.7526482699764188, "count": 63912, "self": 0.0, "children": { "worker_root": { "total": 1986.678526478009, "count": 63912, "is_parallel": true, "self": 836.7079911900075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059779720000392444, "count": 1, "is_parallel": true, "self": 0.003754361999995126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022236100000441184, "count": 8, "is_parallel": true, "self": 0.0022236100000441184 } } }, "UnityEnvironment.step": { "total": 0.04669535400000768, "count": 1, "is_parallel": true, "self": 0.0004604119999953582, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046880399997917266, "count": 1, "is_parallel": true, "self": 0.00046880399997917266 }, "communicator.exchange": { "total": 0.04422156100002894, "count": 1, "is_parallel": true, "self": 0.04422156100002894 }, "steps_from_proto": { "total": 0.0015445770000042103, "count": 1, "is_parallel": true, "self": 0.00041523999993842153, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011293370000657887, "count": 8, "is_parallel": true, "self": 0.0011293370000657887 } } } } } } }, "UnityEnvironment.step": { "total": 1149.9705352880014, "count": 63911, "is_parallel": true, "self": 27.019658076033465, "children": { "UnityEnvironment._generate_step_input": { "total": 22.536683795011015, "count": 63911, "is_parallel": true, "self": 22.536683795011015 }, "communicator.exchange": { "total": 1008.7898858069508, "count": 63911, "is_parallel": true, "self": 1008.7898858069508 }, "steps_from_proto": { "total": 91.62430761000616, "count": 63911, "is_parallel": true, "self": 21.684424702040076, "children": { "_process_rank_one_or_two_observation": { "total": 69.93988290796608, "count": 511288, "is_parallel": true, "self": 69.93988290796608 } } } } } } } } } } }, "trainer_advance": { "total": 629.8163343089938, "count": 63912, "self": 2.300914438999257, "children": { "process_trajectory": { "total": 144.83234555399395, "count": 63912, "self": 144.63969456799418, "children": { "RLTrainer._checkpoint": { "total": 0.19265098599976227, "count": 2, "self": 0.19265098599976227 } } }, "_update_policy": { "total": 482.6830743160006, "count": 453, "self": 180.87082364101963, "children": { "TorchPPOOptimizer.update": { "total": 301.812250674981, "count": 22815, "self": 301.812250674981 } } } } } } }, "trainer_threads": { "total": 1.5450000319106039e-06, "count": 1, "self": 1.5450000319106039e-06 }, "TrainerController._save_models": { "total": 0.08510402599995359, "count": 1, "self": 0.0013982679997752712, "children": { "RLTrainer._checkpoint": { "total": 0.08370575800017832, "count": 1, "self": 0.08370575800017832 } } } } } } }