{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4760575592517853, "min": 0.44958382844924927, "max": 1.4447507858276367, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14258.8759765625, "min": 13401.1943359375, "max": 43827.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989947.0, "min": 29952.0, "max": 989947.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989947.0, "min": 29952.0, "max": 989947.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.28878912329673767, "min": -0.10058929026126862, "max": 0.3379310071468353, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 74.79638671875, "min": -24.242019653320312, "max": 87.862060546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005011674948036671, "min": -0.012146531604230404, "max": 0.27366533875465393, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2980238199234009, "min": -3.145951747894287, "max": 65.67967987060547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06757812375888331, "min": 0.06518831751438686, "max": 0.07297336461162063, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0136718563832496, "min": 0.47755458041919857, "max": 1.0442221518742907, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014149559902661065, "min": 8.970422075490735e-05, "max": 0.014321396636782493, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21224339853991597, "min": 0.0011661548698137956, "max": 0.21224339853991597, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.523797492099999e-06, "min": 7.523797492099999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011285696238149998, "min": 0.00011285696238149998, "max": 0.0035077160307613996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250790000000001, "min": 0.10250790000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376185000000002, "min": 1.3691136000000002, "max": 2.5692386000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002605392099999999, "min": 0.0002605392099999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003908088149999999, "min": 0.003908088149999999, "max": 0.11694693614000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010158954188227654, "min": 0.010158954188227654, "max": 0.40260711312294006, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15238431096076965, "min": 0.146846204996109, "max": 2.8182497024536133, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 512.3620689655172, "min": 469.8305084745763, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29717.0, "min": 15984.0, "max": 32767.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.108210320359674, "min": -1.0000000521540642, "max": 1.258905058695098, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.27619858086109, "min": -32.000001668930054, "max": 74.27539846301079, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.108210320359674, "min": -1.0000000521540642, "max": 1.258905058695098, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.27619858086109, "min": -32.000001668930054, "max": 74.27539846301079, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05595491645488374, "min": 0.05595491645488374, "max": 8.131531807594001, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.245385154383257, "min": 3.245385154383257, "max": 130.10450892150402, "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": "1681981027", "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": "1681983074" }, "total": 2047.525569463, "count": 1, "self": 0.49687851499993485, "children": { "run_training.setup": { "total": 0.10274189400001887, "count": 1, "self": 0.10274189400001887 }, "TrainerController.start_learning": { "total": 2046.925949054, "count": 1, "self": 1.39975699598358, "children": { "TrainerController._reset_env": { "total": 3.7579522920000272, "count": 1, "self": 3.7579522920000272 }, "TrainerController.advance": { "total": 2041.674608881016, "count": 63416, "self": 1.388012196036243, "children": { "env_step": { "total": 1433.1168982120182, "count": 63416, "self": 1327.8318178700067, "children": { "SubprocessEnvManager._take_step": { "total": 104.45314004299667, "count": 63416, "self": 4.641401776004841, "children": { "TorchPolicy.evaluate": { "total": 99.81173826699182, "count": 62574, "self": 99.81173826699182 } } }, "workers": { "total": 0.8319402990148319, "count": 63416, "self": 0.0, "children": { "worker_root": { "total": 2041.9905809119393, "count": 63416, "is_parallel": true, "self": 822.7798758429433, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016996469998957764, "count": 1, "is_parallel": true, "self": 0.0005336029998943559, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011660440000014205, "count": 8, "is_parallel": true, "self": 0.0011660440000014205 } } }, "UnityEnvironment.step": { "total": 0.04896989899998516, "count": 1, "is_parallel": true, "self": 0.0005100639998545375, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005270599999676051, "count": 1, "is_parallel": true, "self": 0.0005270599999676051 }, "communicator.exchange": { "total": 0.04630072200006907, "count": 1, "is_parallel": true, "self": 0.04630072200006907 }, "steps_from_proto": { "total": 0.001632053000093947, "count": 1, "is_parallel": true, "self": 0.0003836359996967076, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012484170003972395, "count": 8, "is_parallel": true, "self": 0.0012484170003972395 } } } } } } }, "UnityEnvironment.step": { "total": 1219.210705068996, "count": 63415, "is_parallel": true, "self": 31.801425920095653, "children": { "UnityEnvironment._generate_step_input": { "total": 22.598281498923825, "count": 63415, "is_parallel": true, "self": 22.598281498923825 }, "communicator.exchange": { "total": 1072.0807667890026, "count": 63415, "is_parallel": true, "self": 1072.0807667890026 }, "steps_from_proto": { "total": 92.73023086097396, "count": 63415, "is_parallel": true, "self": 19.744753526010754, "children": { "_process_rank_one_or_two_observation": { "total": 72.9854773349632, "count": 507320, "is_parallel": true, "self": 72.9854773349632 } } } } } } } } } } }, "trainer_advance": { "total": 607.1696984729615, "count": 63416, "self": 2.527688193958511, "children": { "process_trajectory": { "total": 102.20555095000145, "count": 63416, "self": 101.99071076200153, "children": { "RLTrainer._checkpoint": { "total": 0.21484018799992555, "count": 2, "self": 0.21484018799992555 } } }, "_update_policy": { "total": 502.43645932900154, "count": 441, "self": 320.78384698198465, "children": { "TorchPPOOptimizer.update": { "total": 181.65261234701688, "count": 22863, "self": 181.65261234701688 } } } } } } }, "trainer_threads": { "total": 9.260002116207033e-07, "count": 1, "self": 9.260002116207033e-07 }, "TrainerController._save_models": { "total": 0.09362995900028181, "count": 1, "self": 0.0015444840005329752, "children": { "RLTrainer._checkpoint": { "total": 0.09208547499974884, "count": 1, "self": 0.09208547499974884 } } } } } } }