{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.012792897410690784, "min": 0.012792897410690784, "max": 1.4177621603012085, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 383.1728515625, "min": 383.1728515625, "max": 43009.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09858796745538712, "min": -0.10970687121152878, "max": 0.09507052600383759, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -23.562524795532227, "min": -26.329648971557617, "max": 22.531715393066406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.47252652049064636, "min": 0.31983697414398193, "max": 0.5097172260284424, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 112.933837890625, "min": 75.80136108398438, "max": 122.3321304321289, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06890268857137026, "min": 0.06565859583221718, "max": 0.0739442317207423, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9646376399991836, "min": 0.5052951602322109, "max": 1.0079328600365653, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0002069361613492926, "min": 0.0002069361613492926, "max": 0.017477962049152012, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0028971062588900964, "min": 0.0028971062588900964, "max": 0.12234573434406408, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.389311822642855e-06, "min": 7.389311822642855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010345036551699998, "min": 0.00010345036551699998, "max": 0.0036333355888882, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246307142857143, "min": 0.10246307142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434483, "min": 1.3886848, "max": 2.6111118000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025606083571428565, "min": 0.00025606083571428565, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035848516999999994, "min": 0.0035848516999999994, "max": 0.12113006881999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.46683868765830994, "min": 0.3517557680606842, "max": 0.5818276405334473, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 6.535741806030273, "min": 3.5791425704956055, "max": 6.968112945556641, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 933.7647058823529, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 24975.0, "min": 15984.0, "max": 33719.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9996160507202149, "min": -1.0000000521540642, "max": -0.6991353444755077, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -24.99040126800537, "min": -31.99320164322853, "max": -16.000000834465027, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9996160507202149, "min": -1.0000000521540642, "max": -0.6991353444755077, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -24.99040126800537, "min": -31.99320164322853, "max": -16.000000834465027, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 4.554214012026787, "min": 3.4498045127237997, "max": 10.316271374002099, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 113.85535030066967, "min": 103.89716279879212, "max": 165.06034198403358, "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": "1742547451", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742549325" }, "total": 1873.8962596849997, "count": 1, "self": 0.47661563899873727, "children": { "run_training.setup": { "total": 0.02544095500070398, "count": 1, "self": 0.02544095500070398 }, "TrainerController.start_learning": { "total": 1873.3942030910002, "count": 1, "self": 1.4551815930381053, "children": { "TrainerController._reset_env": { "total": 2.344630540000253, "count": 1, "self": 2.344630540000253 }, "TrainerController.advance": { "total": 1869.5091446499619, "count": 62955, "self": 1.4677964751081163, "children": { "env_step": { "total": 1204.084720821912, "count": 62955, "self": 1043.61177364795, "children": { "SubprocessEnvManager._take_step": { "total": 159.63871706902864, "count": 62955, "self": 4.7038176009173185, "children": { "TorchPolicy.evaluate": { "total": 154.93489946811133, "count": 62555, "self": 154.93489946811133 } } }, "workers": { "total": 0.83423010493334, "count": 62955, "self": 0.0, "children": { "worker_root": { "total": 1868.6862986288215, "count": 62955, "is_parallel": true, "self": 937.7341271886189, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001985984000384633, "count": 1, "is_parallel": true, "self": 0.0006565390012838179, "children": { "_process_rank_one_or_two_observation": { "total": 0.001329444999100815, "count": 8, "is_parallel": true, "self": 0.001329444999100815 } } }, "UnityEnvironment.step": { "total": 0.05082202999983565, "count": 1, "is_parallel": true, "self": 0.0005418070004452602, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046712499988643685, "count": 1, "is_parallel": true, "self": 0.00046712499988643685 }, "communicator.exchange": { "total": 0.04818268199960585, "count": 1, "is_parallel": true, "self": 0.04818268199960585 }, "steps_from_proto": { "total": 0.001630415999898105, "count": 1, "is_parallel": true, "self": 0.00035441700129013043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012759989986079745, "count": 8, "is_parallel": true, "self": 0.0012759989986079745 } } } } } } }, "UnityEnvironment.step": { "total": 930.9521714402026, "count": 62954, "is_parallel": true, "self": 31.97181903335604, "children": { "UnityEnvironment._generate_step_input": { "total": 22.98285553290407, "count": 62954, "is_parallel": true, "self": 22.98285553290407 }, "communicator.exchange": { "total": 779.7476971829592, "count": 62954, "is_parallel": true, "self": 779.7476971829592 }, "steps_from_proto": { "total": 96.24979969098331, "count": 62954, "is_parallel": true, "self": 19.586760796652925, "children": { "_process_rank_one_or_two_observation": { "total": 76.66303889433038, "count": 503632, "is_parallel": true, "self": 76.66303889433038 } } } } } } } } } } }, "trainer_advance": { "total": 663.9566273529417, "count": 62955, "self": 2.5653669250350504, "children": { "process_trajectory": { "total": 124.3180993479009, "count": 62955, "self": 124.11723456190066, "children": { "RLTrainer._checkpoint": { "total": 0.20086478600023838, "count": 2, "self": 0.20086478600023838 } } }, "_update_policy": { "total": 537.0731610800058, "count": 439, "self": 295.15018432397846, "children": { "TorchPPOOptimizer.update": { "total": 241.9229767560273, "count": 22743, "self": 241.9229767560273 } } } } } } }, "trainer_threads": { "total": 1.0889998520724475e-06, "count": 1, "self": 1.0889998520724475e-06 }, "TrainerController._save_models": { "total": 0.08524521900017135, "count": 1, "self": 0.0019105699993815506, "children": { "RLTrainer._checkpoint": { "total": 0.0833346490007898, "count": 1, "self": 0.0833346490007898 } } } } } } }