{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17227934300899506, "min": 0.14775557816028595, "max": 1.4635984897613525, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5184.9189453125, "min": 4461.03662109375, "max": 41402.2734375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999975.0, "min": 29952.0, "max": 2999975.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999975.0, "min": 29952.0, "max": 2999975.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8337558507919312, "min": -0.10874564945697784, "max": 0.843109667301178, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 249.29299926757812, "min": -26.098955154418945, "max": 253.77601623535156, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019505340605974197, "min": -0.020007967948913574, "max": 0.38964346051216125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.832097053527832, "min": -5.062016010284424, "max": 93.4489517211914, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06782731030681576, "min": 0.06502630004840847, "max": 0.07371179427589976, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9495823442954205, "min": 0.42045852671770095, "max": 1.0926284174136383, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017275316234666944, "min": 0.00012379643931509544, "max": 0.017939499105617544, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2418544272853372, "min": 0.001609353711096241, "max": 0.26440839121156995, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4122423864285703e-06, "min": 1.4122423864285703e-06, "max": 0.00029838080053973324, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.9771393409999985e-05, "min": 1.9771393409999985e-05, "max": 0.0040110340629886665, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047071428571429, "min": 0.10047071428571429, "max": 0.1994602666666667, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.40659, "min": 1.1967616, "max": 2.7370113333333332, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.702435714285711e-05, "min": 5.702435714285711e-05, "max": 0.00994608064, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0007983409999999996, "min": 0.0007983409999999996, "max": 0.1337074322, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008908947929739952, "min": 0.008321715518832207, "max": 0.5763432383537292, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12472527474164963, "min": 0.11650402098894119, "max": 3.458059310913086, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 229.57692307692307, "min": 209.2651515151515, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29845.0, "min": 15984.0, "max": 32799.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7553786148551767, "min": -1.0000000521540642, "max": 1.7898571331025963, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 229.95459854602814, "min": -30.99880161881447, "max": 239.05779875814915, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7553786148551767, "min": -1.0000000521540642, "max": 1.7898571331025963, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 229.95459854602814, "min": -30.99880161881447, "max": 239.05779875814915, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.021251703428385782, "min": 0.019405346921104825, "max": 10.395328998565674, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7839731491185375, "min": 2.5517875506193377, "max": 166.32526397705078, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700220916", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700232183" }, "total": 11267.413533334999, "count": 1, "self": 0.7018373039973085, "children": { "run_training.setup": { "total": 0.05388978099995256, "count": 1, "self": 0.05388978099995256 }, "TrainerController.start_learning": { "total": 11266.657806250001, "count": 1, "self": 7.033625984437094, "children": { "TrainerController._reset_env": { "total": 1.4888619790001485, "count": 1, "self": 1.4888619790001485 }, "TrainerController.advance": { "total": 11258.047924498564, "count": 194078, "self": 7.519105631798084, "children": { "env_step": { "total": 7696.921176641046, "count": 194078, "self": 7201.602815548918, "children": { "SubprocessEnvManager._take_step": { "total": 491.0536566050728, "count": 194078, "self": 22.169732687814758, "children": { "TorchPolicy.evaluate": { "total": 468.883923917258, "count": 187442, "self": 468.883923917258 } } }, "workers": { "total": 4.264704487054814, "count": 194078, "self": 0.0, "children": { "worker_root": { "total": 11246.013914505198, "count": 194078, "is_parallel": true, "self": 4589.120808252283, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020163880001291545, "count": 1, "is_parallel": true, "self": 0.0006613190007556113, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013550689993735432, "count": 8, "is_parallel": true, "self": 0.0013550689993735432 } } }, "UnityEnvironment.step": { "total": 0.063354691999848, "count": 1, "is_parallel": true, "self": 0.0006633819998569379, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005039820000547479, "count": 1, "is_parallel": true, "self": 0.0005039820000547479 }, "communicator.exchange": { "total": 0.06030596000005062, "count": 1, "is_parallel": true, "self": 0.06030596000005062 }, "steps_from_proto": { "total": 0.001881367999885697, "count": 1, "is_parallel": true, "self": 0.000408354999990479, "children": { "_process_rank_one_or_two_observation": { "total": 0.001473012999895218, "count": 8, "is_parallel": true, "self": 0.001473012999895218 } } } } } } }, "UnityEnvironment.step": { "total": 6656.8931062529155, "count": 194077, "is_parallel": true, "self": 141.25042082578238, "children": { "UnityEnvironment._generate_step_input": { "total": 86.52563229296698, "count": 194077, "is_parallel": true, "self": 86.52563229296698 }, "communicator.exchange": { "total": 6032.413204861289, "count": 194077, "is_parallel": true, "self": 6032.413204861289 }, "steps_from_proto": { "total": 396.7038482728765, "count": 194077, "is_parallel": true, "self": 85.62810693444749, "children": { "_process_rank_one_or_two_observation": { "total": 311.075741338429, "count": 1552616, "is_parallel": true, "self": 311.075741338429 } } } } } } } } } } }, "trainer_advance": { "total": 3553.60764222572, "count": 194078, "self": 14.509221368961335, "children": { "process_trajectory": { "total": 514.12454919278, "count": 194078, "self": 513.5800037657812, "children": { "RLTrainer._checkpoint": { "total": 0.5445454269988659, "count": 6, "self": 0.5445454269988659 } } }, "_update_policy": { "total": 3024.9738716639786, "count": 1397, "self": 1221.6710247917838, "children": { "TorchPPOOptimizer.update": { "total": 1803.3028468721948, "count": 68334, "self": 1803.3028468721948 } } } } } } }, "trainer_threads": { "total": 1.1230004020035267e-06, "count": 1, "self": 1.1230004020035267e-06 }, "TrainerController._save_models": { "total": 0.08739266500015219, "count": 1, "self": 0.003480690000287723, "children": { "RLTrainer._checkpoint": { "total": 0.08391197499986447, "count": 1, "self": 0.08391197499986447 } } } } } } }