| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.42936721444129944, |
| "min": 0.4079577326774597, |
| "max": 1.4105356931686401, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 12688.66015625, |
| "min": 12290.9501953125, |
| "max": 42790.01171875, |
| "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": 0.33594948053359985, |
| "min": -0.1023218110203743, |
| "max": 0.33594948053359985, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 88.01876068115234, |
| "min": -24.454912185668945, |
| "max": 88.01876068115234, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.06514112651348114, |
| "min": -0.056105900555849075, |
| "max": 0.4652940332889557, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 17.066974639892578, |
| "min": -14.531428337097168, |
| "max": 110.27468872070312, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07143874267404456, |
| "min": 0.06499356928412983, |
| "max": 0.0726657571204702, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0001423974366237, |
| "min": 0.4971758383620616, |
| "max": 1.066078942739599, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.012448190057815127, |
| "min": 0.00017513292127961744, |
| "max": 0.013729920584915411, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.17427466080941179, |
| "min": 0.002276727976635027, |
| "max": 0.20594880877373117, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.545547484850002e-06, |
| "min": 7.545547484850002e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010563766478790003, |
| "min": 0.00010563766478790003, |
| "max": 0.0036319999893334, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10251514999999999, |
| "min": 0.10251514999999999, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4352120999999998, |
| "min": 1.3886848, |
| "max": 2.6106666, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00026126348500000014, |
| "min": 0.00026126348500000014, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003657688790000002, |
| "min": 0.003657688790000002, |
| "max": 0.12108559334, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.014037457294762135, |
| "min": 0.014037457294762135, |
| "max": 0.5005728006362915, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.19652439653873444, |
| "min": 0.19652439653873444, |
| "max": 3.50400972366333, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 481.125, |
| "min": 481.125, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30792.0, |
| "min": 15984.0, |
| "max": 33038.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.3000780997099355, |
| "min": -1.0000000521540642, |
| "max": 1.3000780997099355, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 83.20499838143587, |
| "min": -31.998401671648026, |
| "max": 83.20499838143587, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.3000780997099355, |
| "min": -1.0000000521540642, |
| "max": 1.3000780997099355, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 83.20499838143587, |
| "min": -31.998401671648026, |
| "max": 83.20499838143587, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.06973139011779494, |
| "min": 0.06973139011779494, |
| "max": 10.674522619694471, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.4628089675388765, |
| "min": 4.4628089675388765, |
| "max": 170.79236191511154, |
| "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": "1735544843", |
| "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.5.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1735547955" |
| }, |
| "total": 3111.7487773189996, |
| "count": 1, |
| "self": 0.5971211189989845, |
| "children": { |
| "run_training.setup": { |
| "total": 0.07640626700049324, |
| "count": 1, |
| "self": 0.07640626700049324 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3111.075249933, |
| "count": 1, |
| "self": 2.3042723900671263, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.920334145999732, |
| "count": 1, |
| "self": 2.920334145999732 |
| }, |
| "TrainerController.advance": { |
| "total": 3105.7692443389333, |
| "count": 63430, |
| "self": 2.6905945258695283, |
| "children": { |
| "env_step": { |
| "total": 1997.6885803069708, |
| "count": 63430, |
| "self": 1830.6064573751282, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 165.71613637401606, |
| "count": 63430, |
| "self": 7.023570870971525, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 158.69256550304453, |
| "count": 62563, |
| "self": 158.69256550304453 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.3659865578265453, |
| "count": 63430, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3104.215387741081, |
| "count": 63430, |
| "is_parallel": true, |
| "self": 1450.5358200799146, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0032038640001701424, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0010785740023493418, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0021252899978208006, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0021252899978208006 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.06257491999986087, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007469159991160268, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.000521025000125519, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000521025000125519 |
| }, |
| "communicator.exchange": { |
| "total": 0.05930874200021208, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05930874200021208 |
| }, |
| "steps_from_proto": { |
| "total": 0.0019982370004072436, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00040232700030173874, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015959100001055049, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015959100001055049 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1653.6795676611664, |
| "count": 63429, |
| "is_parallel": true, |
| "self": 49.176004906251364, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 30.292051162044118, |
| "count": 63429, |
| "is_parallel": true, |
| "self": 30.292051162044118 |
| }, |
| "communicator.exchange": { |
| "total": 1444.9008156819937, |
| "count": 63429, |
| "is_parallel": true, |
| "self": 1444.9008156819937 |
| }, |
| "steps_from_proto": { |
| "total": 129.31069591087726, |
| "count": 63429, |
| "is_parallel": true, |
| "self": 27.290113336644026, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 102.02058257423323, |
| "count": 507432, |
| "is_parallel": true, |
| "self": 102.02058257423323 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1105.390069506093, |
| "count": 63430, |
| "self": 4.292966431021341, |
| "children": { |
| "process_trajectory": { |
| "total": 166.69363949906074, |
| "count": 63430, |
| "self": 166.48721100606144, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.20642849299929367, |
| "count": 2, |
| "self": 0.20642849299929367 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 934.4034635760108, |
| "count": 448, |
| "self": 375.89692145393565, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 558.5065421220752, |
| "count": 22809, |
| "self": 558.5065421220752 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0690000635804608e-06, |
| "count": 1, |
| "self": 1.0690000635804608e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08139798899992456, |
| "count": 1, |
| "self": 0.0022283440002865973, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07916964499963797, |
| "count": 1, |
| "self": 0.07916964499963797 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
