{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6857642531394958, "min": 0.6857642531394958, "max": 1.4782092571258545, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 20452.232421875, "min": 20452.232421875, "max": 44842.95703125, "count": 10 }, "Pyramids.Step.mean": { "value": 299875.0, "min": 29952.0, "max": 299875.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299875.0, "min": 29952.0, "max": 299875.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08650875091552734, "min": -0.16226035356521606, "max": -0.05395248904824257, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -20.762100219726562, "min": -38.45570373535156, "max": -13.110454559326172, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.038227494806051254, "min": 0.038227494806051254, "max": 0.25249892473220825, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.174598693847656, "min": 9.174598693847656, "max": 60.5997428894043, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06621371803462482, "min": 0.06621371803462482, "max": 0.07140908086001309, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8607783344501226, "min": 0.4946522531454216, "max": 0.9805612934831671, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0010210787272243063, "min": 0.0010210787272243063, "max": 0.006060343406106811, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.01327402345391598, "min": 0.01327402345391598, "max": 0.042422403842747675, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5054018058948717e-05, "min": 1.5054018058948717e-05, "max": 0.0002838354339596191, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00019570223476633332, "min": 0.00019570223476633332, "max": 0.0024611702796100005, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10501797435897438, "min": 0.10501797435897438, "max": 0.19461180952380958, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.365233666666667, "min": 1.362282666666667, "max": 2.032080666666667, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005112956384615383, "min": 0.0005112956384615383, "max": 0.00946171977142857, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.006646843299999998, "min": 0.006646843299999998, "max": 0.082066961, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03791473060846329, "min": 0.03791473060846329, "max": 0.4183076322078705, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.49289149045944214, "min": 0.49289149045944214, "max": 2.9281535148620605, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 985.9677419354839, "min": 927.3030303030303, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30565.0, "min": 15984.0, "max": 32356.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9221355367091394, "min": -1.0000000521540642, "max": -0.6249030781063166, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -28.586201637983322, "min": -29.99300166219473, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9221355367091394, "min": -1.0000000521540642, "max": -0.6249030781063166, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -28.586201637983322, "min": -29.99300166219473, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.3934369310135803, "min": 0.3934369310135803, "max": 8.543423502705991, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 12.196544861420989, "min": 10.666800018399954, "max": 136.69477604329586, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718358598", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718359186" }, "total": 587.3496648420002, "count": 1, "self": 0.5282119700001431, "children": { "run_training.setup": { "total": 0.0785807479999221, "count": 1, "self": 0.0785807479999221 }, "TrainerController.start_learning": { "total": 586.7428721240001, "count": 1, "self": 0.37381806600171785, "children": { "TrainerController._reset_env": { "total": 2.4277736110000205, "count": 1, "self": 2.4277736110000205 }, "TrainerController.advance": { "total": 583.8317824519983, "count": 18905, "self": 0.4029481010067002, "children": { "env_step": { "total": 393.4856471010082, "count": 18905, "self": 354.1138093499974, "children": { "SubprocessEnvManager._take_step": { "total": 39.146488250014954, "count": 18905, "self": 1.3435121500174318, "children": { "TorchPolicy.evaluate": { "total": 37.80297609999752, "count": 18801, "self": 37.80297609999752 } } }, "workers": { "total": 0.22534950099588968, "count": 18905, "self": 0.0, "children": { "worker_root": { "total": 585.3678140970013, "count": 18905, "is_parallel": true, "self": 265.658549171, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019624290000592737, "count": 1, "is_parallel": true, "self": 0.000582765000103791, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013796639999554827, "count": 8, "is_parallel": true, "self": 0.0013796639999554827 } } }, "UnityEnvironment.step": { "total": 0.04633306799996717, "count": 1, "is_parallel": true, "self": 0.0006468049999739378, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004530630000090241, "count": 1, "is_parallel": true, "self": 0.0004530630000090241 }, "communicator.exchange": { "total": 0.0436490810000123, "count": 1, "is_parallel": true, "self": 0.0436490810000123 }, "steps_from_proto": { "total": 0.0015841189999719063, "count": 1, "is_parallel": true, "self": 0.000339096999823596, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012450220001483103, "count": 8, "is_parallel": true, "self": 0.0012450220001483103 } } } } } } }, "UnityEnvironment.step": { "total": 319.7092649260013, "count": 18904, "is_parallel": true, "self": 9.844938205995845, "children": { "UnityEnvironment._generate_step_input": { "total": 6.673449753999989, "count": 18904, "is_parallel": true, "self": 6.673449753999989 }, "communicator.exchange": { "total": 275.0330481049888, "count": 18904, "is_parallel": true, "self": 275.0330481049888 }, "steps_from_proto": { "total": 28.157828861016696, "count": 18904, "is_parallel": true, "self": 5.544785575991568, "children": { "_process_rank_one_or_two_observation": { "total": 22.613043285025128, "count": 151232, "is_parallel": true, "self": 22.613043285025128 } } } } } } } } } } }, "trainer_advance": { "total": 189.94318724998334, "count": 18905, "self": 0.5889082929655842, "children": { "process_trajectory": { "total": 36.676568237016, "count": 18905, "self": 36.676568237016 }, "_update_policy": { "total": 152.67771072000176, "count": 120, "self": 90.09042442700434, "children": { "TorchPPOOptimizer.update": { "total": 62.58728629299742, "count": 6858, "self": 62.58728629299742 } } } } } } }, "trainer_threads": { "total": 7.769999683659989e-07, "count": 1, "self": 7.769999683659989e-07 }, "TrainerController._save_models": { "total": 0.10949721800011503, "count": 1, "self": 0.001699325000117824, "children": { "RLTrainer._checkpoint": { "total": 0.1077978929999972, "count": 1, "self": 0.1077978929999972 } } } } } } }