{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34867730736732483, "min": 0.34867730736732483, "max": 1.388346552848816, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 10477.0556640625, "min": 10477.0556640625, "max": 42116.8828125, "count": 34 }, "Pyramids.Step.mean": { "value": 1019966.0, "min": 29952.0, "max": 1019966.0, "count": 34 }, "Pyramids.Step.sum": { "value": 1019966.0, "min": 29952.0, "max": 1019966.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.593503475189209, "min": -0.09624023735523224, "max": 0.6029665470123291, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.43295288085938, "min": -23.290138244628906, "max": 168.83062744140625, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026628784835338593, "min": 0.019439801573753357, "max": 0.3245362639427185, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.243029594421387, "min": 5.287626266479492, "max": 78.21324157714844, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0726065815991203, "min": 0.06518121377733067, "max": 0.0738082705479396, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0164921423876843, "min": 0.4951569713843148, "max": 1.0532709674056, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013795891233837442, "min": 0.00022016958157364307, "max": 0.016662508809246242, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1931424772737242, "min": 0.002642034978883717, "max": 0.2332751233294474, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019953571205953572, "min": 0.00019953571205953572, "max": 0.00029838354339596195, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027934999688335, "min": 0.0020886848037717336, "max": 0.004072620342459933, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16651189285714288, "min": 0.16651189285714288, "max": 0.19946118095238097, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3311665, "min": 1.3962282666666668, "max": 2.857540066666667, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 0.006654538096428571, "min": 0.006654538096428571, "max": 0.009946171977142856, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.09316353335, "min": 0.06962320384, "max": 0.13576825266, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.021514538675546646, "min": 0.019645169377326965, "max": 0.45205339789390564, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.30120354890823364, "min": 0.2750323712825775, "max": 3.1643738746643066, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 363.6125, "min": 321.8510638297872, "max": 999.0, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29089.0, "min": 15984.0, "max": 32456.0, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5113474772311748, "min": -1.0000000521540642, "max": 1.6568701980595892, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.90779817849398, "min": -31.998001664876938, "max": 155.7457986176014, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5113474772311748, "min": -1.0000000521540642, "max": 1.6568701980595892, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.90779817849398, "min": -31.998001664876938, "max": 155.7457986176014, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08085155892549664, "min": 0.0660823707253502, "max": 9.158712689764798, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 6.468124714039732, "min": 5.902974153170362, "max": 146.53940303623676, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711912175", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711916143" }, "total": 3967.928722861, "count": 1, "self": 0.5304992470000798, "children": { "run_training.setup": { "total": 0.0689880190002441, "count": 1, "self": 0.0689880190002441 }, "TrainerController.start_learning": { "total": 3967.329235595, "count": 1, "self": 2.783447556980718, "children": { "TrainerController._reset_env": { "total": 2.9833197799998743, "count": 1, "self": 2.9833197799998743 }, "TrainerController.advance": { "total": 3961.4013934760187, "count": 65943, "self": 3.0230258670521835, "children": { "env_step": { "total": 2676.8190595849724, "count": 65943, "self": 2471.335659888868, "children": { "SubprocessEnvManager._take_step": { "total": 203.7215361380886, "count": 65943, "self": 8.738868755081512, "children": { "TorchPolicy.evaluate": { "total": 194.98266738300708, "count": 64487, "self": 194.98266738300708 } } }, "workers": { "total": 1.7618635580156479, "count": 65942, "self": 0.0, "children": { "worker_root": { "total": 3959.3801244119204, "count": 65942, "is_parallel": true, "self": 1717.3903096018576, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035716060001504957, "count": 1, "is_parallel": true, "self": 0.0010753879996627802, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024962180004877155, "count": 8, "is_parallel": true, "self": 0.0024962180004877155 } } }, "UnityEnvironment.step": { "total": 0.07145232299990312, "count": 1, "is_parallel": true, "self": 0.0007847249994483718, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033339300034640473, "count": 1, "is_parallel": true, "self": 0.00033339300034640473 }, "communicator.exchange": { "total": 0.06824412100013433, "count": 1, "is_parallel": true, "self": 0.06824412100013433 }, "steps_from_proto": { "total": 0.002090083999974013, "count": 1, "is_parallel": true, "self": 0.0004403819998515246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016497020001224882, "count": 8, "is_parallel": true, "self": 0.0016497020001224882 } } } } } } }, "UnityEnvironment.step": { "total": 2241.989814810063, "count": 65941, "is_parallel": true, "self": 60.44033313942464, "children": { "UnityEnvironment._generate_step_input": { "total": 32.60185797985423, "count": 65941, "is_parallel": true, "self": 32.60185797985423 }, "communicator.exchange": { "total": 2000.7793568549287, "count": 65941, "is_parallel": true, "self": 2000.7793568549287 }, "steps_from_proto": { "total": 148.16826683585532, "count": 65941, "is_parallel": true, "self": 33.26586393802609, "children": { "_process_rank_one_or_two_observation": { "total": 114.90240289782923, "count": 527528, "is_parallel": true, "self": 114.90240289782923 } } } } } } } } } } }, "trainer_advance": { "total": 1281.5593080239942, "count": 65942, "self": 6.257364301982307, "children": { "process_trajectory": { "total": 203.62035893600614, "count": 65942, "self": 203.41450901600683, "children": { "RLTrainer._checkpoint": { "total": 0.20584991999930935, "count": 2, "self": 0.20584991999930935 } } }, "_update_policy": { "total": 1071.6815847860057, "count": 464, "self": 415.06280488803486, "children": { "TorchPPOOptimizer.update": { "total": 656.6187798979709, "count": 23553, "self": 656.6187798979709 } } } } } } }, "trainer_threads": { "total": 1.965000592463184e-06, "count": 1, "self": 1.965000592463184e-06 }, "TrainerController._save_models": { "total": 0.16107281699987652, "count": 1, "self": 0.004031147000205237, "children": { "RLTrainer._checkpoint": { "total": 0.15704166999967129, "count": 1, "self": 0.15704166999967129 } } } } } } }