{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42282634973526, "min": 0.4134606122970581, "max": 1.3388434648513794, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12833.625, "min": 12370.7412109375, "max": 40615.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6596373319625854, "min": -0.10541042685508728, "max": 0.6831885576248169, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 186.01773071289062, "min": -24.982271194458008, "max": 195.3919219970703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013017503544688225, "min": -0.05150588974356651, "max": 0.3418310284614563, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.670936107635498, "min": -14.267131805419922, "max": 82.03944396972656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06832212442670771, "min": 0.06495265284760564, "max": 0.07319118431042912, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9565097419739079, "min": 0.4834130873044567, "max": 1.049182909016963, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014718744443685169, "min": 9.216106169313096e-05, "max": 0.016114615501941272, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20606242221159238, "min": 0.0011980938020107025, "max": 0.2256046170271778, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.396918962964285e-06, "min": 7.396918962964285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001035568654815, "min": 0.0001035568654815, "max": 0.0032552654149115997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246560714285713, "min": 0.10246560714285713, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345184999999998, "min": 1.3691136000000002, "max": 2.5275552, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002563141535714286, "min": 0.0002563141535714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00358839815, "min": 0.00358839815, "max": 0.10853033116, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009540995582938194, "min": 0.009540995582938194, "max": 0.533331036567688, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13357393443584442, "min": 0.13357393443584442, "max": 3.7333173751831055, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 295.5480769230769, "min": 274.5238095238095, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30737.0, "min": 15984.0, "max": 32193.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6659865130025606, "min": -1.0000000521540642, "max": 1.7107358323234432, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.2625973522663, "min": -32.000001668930054, "max": 184.05219818651676, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6659865130025606, "min": -1.0000000521540642, "max": 1.7107358323234432, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.2625973522663, "min": -32.000001668930054, "max": 184.05219818651676, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029379365838394733, "min": 0.02922256878288331, "max": 11.625984650105238, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0554540471930522, "min": 3.0305317230377113, "max": 186.0157544016838, "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": "1747562674", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747565140" }, "total": 2465.498817819, "count": 1, "self": 0.7992503969999234, "children": { "run_training.setup": { "total": 0.024509576999946603, "count": 1, "self": 0.024509576999946603 }, "TrainerController.start_learning": { "total": 2464.675057845, "count": 1, "self": 1.6853303219590998, "children": { "TrainerController._reset_env": { "total": 3.7472397159999673, "count": 1, "self": 3.7472397159999673 }, "TrainerController.advance": { "total": 2459.121330734041, "count": 64062, "self": 1.8968836690423814, "children": { "env_step": { "total": 1736.9998128149823, "count": 64062, "self": 1566.471554750045, "children": { "SubprocessEnvManager._take_step": { "total": 169.5352787249708, "count": 64062, "self": 5.117634717931594, "children": { "TorchPolicy.evaluate": { "total": 164.4176440070392, "count": 62576, "self": 164.4176440070392 } } }, "workers": { "total": 0.9929793399663822, "count": 64062, "self": 0.0, "children": { "worker_root": { "total": 2458.6354030429848, "count": 64062, "is_parallel": true, "self": 1020.0667511729657, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005674649000013687, "count": 1, "is_parallel": true, "self": 0.004292326999973284, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013823220000404035, "count": 8, "is_parallel": true, "self": 0.0013823220000404035 } } }, "UnityEnvironment.step": { "total": 0.055261988000040674, "count": 1, "is_parallel": true, "self": 0.0005962070000578024, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004698770000004515, "count": 1, "is_parallel": true, "self": 0.0004698770000004515 }, "communicator.exchange": { "total": 0.050409452999986115, "count": 1, "is_parallel": true, "self": 0.050409452999986115 }, "steps_from_proto": { "total": 0.0037864509999963047, "count": 1, "is_parallel": true, "self": 0.0023861689999762348, "children": { "_process_rank_one_or_two_observation": { "total": 0.00140028200002007, "count": 8, "is_parallel": true, "self": 0.00140028200002007 } } } } } } }, "UnityEnvironment.step": { "total": 1438.568651870019, "count": 64061, "is_parallel": true, "self": 34.940343296047786, "children": { "UnityEnvironment._generate_step_input": { "total": 24.203960918020982, "count": 64061, "is_parallel": true, "self": 24.203960918020982 }, "communicator.exchange": { "total": 1278.4245896459574, "count": 64061, "is_parallel": true, "self": 1278.4245896459574 }, "steps_from_proto": { "total": 100.99975800999277, "count": 64061, "is_parallel": true, "self": 21.046588524103186, "children": { "_process_rank_one_or_two_observation": { "total": 79.95316948588959, "count": 512488, "is_parallel": true, "self": 79.95316948588959 } } } } } } } } } } }, "trainer_advance": { "total": 720.2246342500159, "count": 64062, "self": 3.141840660996877, "children": { "process_trajectory": { "total": 138.62073451302035, "count": 64062, "self": 138.27119032802057, "children": { "RLTrainer._checkpoint": { "total": 0.349544184999786, "count": 2, "self": 0.349544184999786 } } }, "_update_policy": { "total": 578.4620590759987, "count": 446, "self": 319.90692184200833, "children": { "TorchPPOOptimizer.update": { "total": 258.55513723399037, "count": 22851, "self": 258.55513723399037 } } } } } } }, "trainer_threads": { "total": 1.1289998838037718e-06, "count": 1, "self": 1.1289998838037718e-06 }, "TrainerController._save_models": { "total": 0.12115594400029295, "count": 1, "self": 0.0017638550002629927, "children": { "RLTrainer._checkpoint": { "total": 0.11939208900002996, "count": 1, "self": 0.11939208900002996 } } } } } } }