{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2740525007247925, "min": 0.2740525007247925, "max": 1.5402588844299316, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8182.111328125, "min": 8182.111328125, "max": 46725.29296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7320511937141418, "min": -0.0860162153840065, "max": 0.7320511937141418, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 212.2948455810547, "min": -20.729907989501953, "max": 212.2948455810547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019426757469773293, "min": -0.010349159128963947, "max": 0.23527663946151733, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.633759498596191, "min": -2.959859609603882, "max": 56.466392517089844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06607815693792012, "min": 0.06298661256183145, "max": 0.0727185758850759, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9250941971308817, "min": 0.4886501151556551, "max": 1.0748833447555537, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01460864452303763, "min": 0.0009774613464094888, "max": 0.0167398594837249, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2045210233225268, "min": 0.006842229424866422, "max": 0.2343580327721486, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.661776017535713e-06, "min": 7.661776017535713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010726486424549998, "min": 0.00010726486424549998, "max": 0.0036329617890127996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255389285714285, "min": 0.10255389285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357544999999998, "min": 1.3691136000000002, "max": 2.6109872, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002651338964285715, "min": 0.0002651338964285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003711874550000001, "min": 0.003711874550000001, "max": 0.12111762128000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011309400200843811, "min": 0.011309400200843811, "max": 0.39527592062950134, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15833160281181335, "min": 0.15833160281181335, "max": 2.7669315338134766, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 271.7522935779817, "min": 251.86776859504133, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29621.0, "min": 15984.0, "max": 32371.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7106018010865558, "min": -1.0000000521540642, "max": 1.7477999866008758, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 188.16619811952114, "min": -32.000001668930054, "max": 209.7359983921051, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7106018010865558, "min": -1.0000000521540642, "max": 1.7477999866008758, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 188.16619811952114, "min": -32.000001668930054, "max": 209.7359983921051, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03171243051500906, "min": 0.030701358927763066, "max": 8.038420243188739, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.488367356650997, "min": 3.488367356650997, "max": 128.61472389101982, "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": "1704536600", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704539086" }, "total": 2485.462168256, "count": 1, "self": 0.49665773600008833, "children": { "run_training.setup": { "total": 0.05154931200002011, "count": 1, "self": 0.05154931200002011 }, "TrainerController.start_learning": { "total": 2484.913961208, "count": 1, "self": 1.6698278129319988, "children": { "TrainerController._reset_env": { "total": 3.0924113579999357, "count": 1, "self": 3.0924113579999357 }, "TrainerController.advance": { "total": 2480.0631900760677, "count": 64314, "self": 1.7710278030735935, "children": { "env_step": { "total": 1805.4001162789887, "count": 64314, "self": 1654.6496248250808, "children": { "SubprocessEnvManager._take_step": { "total": 149.74779008897406, "count": 64314, "self": 5.4807477519433405, "children": { "TorchPolicy.evaluate": { "total": 144.26704233703072, "count": 62542, "self": 144.26704233703072 } } }, "workers": { "total": 1.0027013649338414, "count": 64314, "self": 0.0, "children": { "worker_root": { "total": 2479.1795190170405, "count": 64314, "is_parallel": true, "self": 961.6578393350635, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0037378690000196, "count": 1, "is_parallel": true, "self": 0.0025774870001669115, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011603819998526888, "count": 8, "is_parallel": true, "self": 0.0011603819998526888 } } }, "UnityEnvironment.step": { "total": 0.053241848999959984, "count": 1, "is_parallel": true, "self": 0.0006492319998869789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004993559999775243, "count": 1, "is_parallel": true, "self": 0.0004993559999775243 }, "communicator.exchange": { "total": 0.050156635000007554, "count": 1, "is_parallel": true, "self": 0.050156635000007554 }, "steps_from_proto": { "total": 0.0019366260000879265, "count": 1, "is_parallel": true, "self": 0.0005196980001755946, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014169279999123319, "count": 8, "is_parallel": true, "self": 0.0014169279999123319 } } } } } } }, "UnityEnvironment.step": { "total": 1517.521679681977, "count": 64313, "is_parallel": true, "self": 38.94968400103994, "children": { "UnityEnvironment._generate_step_input": { "total": 27.54794296497721, "count": 64313, "is_parallel": true, "self": 27.54794296497721 }, "communicator.exchange": { "total": 1337.6674896180016, "count": 64313, "is_parallel": true, "self": 1337.6674896180016 }, "steps_from_proto": { "total": 113.35656309795831, "count": 64313, "is_parallel": true, "self": 23.649676890854835, "children": { "_process_rank_one_or_two_observation": { "total": 89.70688620710348, "count": 514504, "is_parallel": true, "self": 89.70688620710348 } } } } } } } } } } }, "trainer_advance": { "total": 672.8920459940055, "count": 64314, "self": 3.1672955359798607, "children": { "process_trajectory": { "total": 140.4743919440274, "count": 64314, "self": 140.27425966402745, "children": { "RLTrainer._checkpoint": { "total": 0.20013227999993433, "count": 2, "self": 0.20013227999993433 } } }, "_update_policy": { "total": 529.2503585139982, "count": 451, "self": 314.49438980000525, "children": { "TorchPPOOptimizer.update": { "total": 214.75596871399296, "count": 22791, "self": 214.75596871399296 } } } } } } }, "trainer_threads": { "total": 9.360001058666967e-07, "count": 1, "self": 9.360001058666967e-07 }, "TrainerController._save_models": { "total": 0.08853102500006571, "count": 1, "self": 0.00222289399971487, "children": { "RLTrainer._checkpoint": { "total": 0.08630813100035084, "count": 1, "self": 0.08630813100035084 } } } } } } }