{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4291665852069855, "min": 0.4137546718120575, "max": 1.3958520889282227, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12765.130859375, "min": 12386.16015625, "max": 42344.5703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29907.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29907.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5473515391349792, "min": -0.10289521515369415, "max": 0.62845778465271, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.52166748046875, "min": -24.69485092163086, "max": 179.1104736328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00014271757390815765, "min": -0.00035010126885026693, "max": 0.3770541846752167, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.039247334003448486, "min": -0.09977886080741882, "max": 89.9361572265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06808079775781188, "min": 0.0651883091759113, "max": 0.0735750703715859, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9531311686093664, "min": 0.5134848561743408, "max": 1.0841561514283895, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014521952887616481, "min": 0.00025098344614584697, "max": 0.023814089506857282, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20330734042663073, "min": 0.0032627847998960104, "max": 0.21471015267033017, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.446354660771431e-06, "min": 7.446354660771431e-06, "max": 0.00029523484444552854, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010424896525080003, "min": 0.00010424896525080003, "max": 0.0037600177466607996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248208571428574, "min": 0.10248208571428574, "max": 0.19841161428571427, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347492000000004, "min": 1.3888813, "max": 2.6533392, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025796036285714294, "min": 0.00025796036285714294, "max": 0.009841320267142855, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003611445080000001, "min": 0.003611445080000001, "max": 0.12534858608, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010056180879473686, "min": 0.010056180879473686, "max": 0.5892688632011414, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1407865285873413, "min": 0.1407865285873413, "max": 4.124882221221924, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 383.58024691358025, "min": 324.0752688172043, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31070.0, "min": 16578.0, "max": 32666.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6164197353301224, "min": -0.9998000510968268, "max": 1.6555810313475758, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.92999856173992, "min": -31.993601635098457, "max": 157.28019797801971, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6164197353301224, "min": -0.9998000510968268, "max": 1.6555810313475758, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.92999856173992, "min": -31.993601635098457, "max": 157.28019797801971, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03980722840958746, "min": 0.03451729436607198, "max": 12.555591180044061, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2243855011765845, "min": 3.160517840529792, "max": 213.44505006074905, "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": "1724615803", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724618016" }, "total": 2213.0357296600005, "count": 1, "self": 0.526202815000488, "children": { "run_training.setup": { "total": 0.05321369400007825, "count": 1, "self": 0.05321369400007825 }, "TrainerController.start_learning": { "total": 2212.456313151, "count": 1, "self": 1.5703213659189714, "children": { "TrainerController._reset_env": { "total": 2.224209297000016, "count": 1, "self": 2.224209297000016 }, "TrainerController.advance": { "total": 2208.576887235081, "count": 63749, "self": 1.6883311669926115, "children": { "env_step": { "total": 1573.587363303054, "count": 63749, "self": 1432.4220239230096, "children": { "SubprocessEnvManager._take_step": { "total": 140.18988997498468, "count": 63749, "self": 4.8636424950168475, "children": { "TorchPolicy.evaluate": { "total": 135.32624747996783, "count": 62558, "self": 135.32624747996783 } } }, "workers": { "total": 0.975449405059635, "count": 63749, "self": 0.0, "children": { "worker_root": { "total": 2207.1135858350917, "count": 63749, "is_parallel": true, "self": 903.0229202900705, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002062069999965388, "count": 1, "is_parallel": true, "self": 0.0006224429998837877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014396270000816003, "count": 8, "is_parallel": true, "self": 0.0014396270000816003 } } }, "UnityEnvironment.step": { "total": 0.04609425100011322, "count": 1, "is_parallel": true, "self": 0.000639114000250629, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004711700000825658, "count": 1, "is_parallel": true, "self": 0.0004711700000825658 }, "communicator.exchange": { "total": 0.04330912599994008, "count": 1, "is_parallel": true, "self": 0.04330912599994008 }, "steps_from_proto": { "total": 0.0016748409998399438, "count": 1, "is_parallel": true, "self": 0.0003624680002758396, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013123729995641042, "count": 8, "is_parallel": true, "self": 0.0013123729995641042 } } } } } } }, "UnityEnvironment.step": { "total": 1304.0906655450212, "count": 63748, "is_parallel": true, "self": 34.79114804005917, "children": { "UnityEnvironment._generate_step_input": { "total": 23.290424364990486, "count": 63748, "is_parallel": true, "self": 23.290424364990486 }, "communicator.exchange": { "total": 1147.98911158304, "count": 63748, "is_parallel": true, "self": 1147.98911158304 }, "steps_from_proto": { "total": 98.0199815569315, "count": 63748, "is_parallel": true, "self": 20.062352068049677, "children": { "_process_rank_one_or_two_observation": { "total": 77.95762948888182, "count": 509984, "is_parallel": true, "self": 77.95762948888182 } } } } } } } } } } }, "trainer_advance": { "total": 633.3011927650341, "count": 63749, "self": 2.9342313279769314, "children": { "process_trajectory": { "total": 126.00982430105387, "count": 63749, "self": 125.81637040605347, "children": { "RLTrainer._checkpoint": { "total": 0.19345389500040255, "count": 2, "self": 0.19345389500040255 } } }, "_update_policy": { "total": 504.3571371360033, "count": 456, "self": 297.9299433139961, "children": { "TorchPPOOptimizer.update": { "total": 206.4271938220072, "count": 22794, "self": 206.4271938220072 } } } } } } }, "trainer_threads": { "total": 8.790002539171837e-07, "count": 1, "self": 8.790002539171837e-07 }, "TrainerController._save_models": { "total": 0.08489437399975941, "count": 1, "self": 0.0013305950001267774, "children": { "RLTrainer._checkpoint": { "total": 0.08356377899963263, "count": 1, "self": 0.08356377899963263 } } } } } } }