{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3752521872520447, "min": 0.3726296126842499, "max": 1.4241857528686523, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11143.4892578125, "min": 11143.4892578125, "max": 43204.09765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989977.0, "min": 29952.0, "max": 989977.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989977.0, "min": 29952.0, "max": 989977.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5073338747024536, "min": -0.15709273517131805, "max": 0.5073338747024536, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.038818359375, "min": -37.230979919433594, "max": 141.038818359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01064631249755621, "min": -0.014242095872759819, "max": 0.4017970860004425, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.959674835205078, "min": -3.6887028217315674, "max": 95.22590637207031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06888174317317039, "min": 0.06530636204074819, "max": 0.07351751411359556, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9643444044243855, "min": 0.5029900019542493, "max": 1.0571775466646525, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016784855958359827, "min": 0.0001689878474534256, "max": 0.018335733589264127, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23498798341703758, "min": 0.0021968420168945327, "max": 0.25670027024969777, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.66346887411429e-06, "min": 7.66346887411429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010728856423760005, "min": 0.00010728856423760005, "max": 0.0035079350306883995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255445714285714, "min": 0.10255445714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357624, "min": 1.3886848, "max": 2.5725929, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002651902685714287, "min": 0.0002651902685714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003712663760000002, "min": 0.003712663760000002, "max": 0.11695422884000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012414515018463135, "min": 0.011799681931734085, "max": 0.4730353355407715, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1738032102584839, "min": 0.16720174252986908, "max": 3.3112473487854004, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 352.5487804878049, "min": 352.5487804878049, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28909.0, "min": 15984.0, "max": 33176.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5226370242458802, "min": -1.0000000521540642, "max": 1.5797108243028801, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.3335989639163, "min": -31.99360164999962, "max": 131.11599841713905, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5226370242458802, "min": -1.0000000521540642, "max": 1.5797108243028801, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.3335989639163, "min": -31.99360164999962, "max": 131.11599841713905, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.045415635478688564, "min": 0.045415635478688564, "max": 9.601855037733912, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6786664737737738, "min": 3.5155977311660536, "max": 153.6296806037426, "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": "1681202021", "python_version": "3.8.13 (default, Oct 21 2022, 23:50:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/chenoi1/miniconda3/envs/dxtorch/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1", "numpy_version": "1.21.2", "end_time_seconds": "1681202797" }, "total": 776.6553004240013, "count": 1, "self": 0.1669161650024762, "children": { "run_training.setup": { "total": 0.026683390999096446, "count": 1, "self": 0.026683390999096446 }, "TrainerController.start_learning": { "total": 776.4617008679998, "count": 1, "self": 0.520455204998143, "children": { "TrainerController._reset_env": { "total": 0.41397007099658367, "count": 1, "self": 0.41397007099658367 }, "TrainerController.advance": { "total": 775.4998153670058, "count": 63653, "self": 0.46113069788043504, "children": { "env_step": { "total": 544.5502136341602, "count": 63653, "self": 515.54809159879, "children": { "SubprocessEnvManager._take_step": { "total": 28.650736878884345, "count": 63653, "self": 1.5535509100955096, "children": { "TorchPolicy.evaluate": { "total": 27.097185968788835, "count": 62558, "self": 27.097185968788835 } } }, "workers": { "total": 0.35138515648577595, "count": 63653, "self": 0.0, "children": { "worker_root": { "total": 774.9742332089372, "count": 63653, "is_parallel": true, "self": 296.96587168728365, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012302149989409372, "count": 1, "is_parallel": true, "self": 0.0002770469982351642, "children": { "_process_rank_one_or_two_observation": { "total": 0.000953168000705773, "count": 8, "is_parallel": true, "self": 0.000953168000705773 } } }, "UnityEnvironment.step": { "total": 0.02085151600113022, "count": 1, "is_parallel": true, "self": 0.00014925200230209157, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015776999862282537, "count": 1, "is_parallel": true, "self": 0.00015776999862282537 }, "communicator.exchange": { "total": 0.02004688899978646, "count": 1, "is_parallel": true, "self": 0.02004688899978646 }, "steps_from_proto": { "total": 0.0004976050004188437, "count": 1, "is_parallel": true, "self": 0.0001260490062122699, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003715559942065738, "count": 8, "is_parallel": true, "self": 0.0003715559942065738 } } } } } } }, "UnityEnvironment.step": { "total": 478.00836152165357, "count": 63652, "is_parallel": true, "self": 7.678064211802848, "children": { "UnityEnvironment._generate_step_input": { "total": 7.0439759878318, "count": 63652, "is_parallel": true, "self": 7.0439759878318 }, "communicator.exchange": { "total": 441.6234501740473, "count": 63652, "is_parallel": true, "self": 441.6234501740473 }, "steps_from_proto": { "total": 21.6628711479716, "count": 63652, "is_parallel": true, "self": 4.533136689238745, "children": { "_process_rank_one_or_two_observation": { "total": 17.129734458732855, "count": 509216, "is_parallel": true, "self": 17.129734458732855 } } } } } } } } } } }, "trainer_advance": { "total": 230.4884710349652, "count": 63653, "self": 1.0667382667925267, "children": { "process_trajectory": { "total": 36.91444560214222, "count": 63653, "self": 36.85465707414551, "children": { "RLTrainer._checkpoint": { "total": 0.05978852799671586, "count": 2, "self": 0.05978852799671586 } } }, "_update_policy": { "total": 192.50728716603044, "count": 453, "self": 107.02853807108477, "children": { "TorchPPOOptimizer.update": { "total": 85.47874909494567, "count": 22800, "self": 85.47874909494567 } } } } } } }, "trainer_threads": { "total": 3.4099866752512753e-07, "count": 1, "self": 3.4099866752512753e-07 }, "TrainerController._save_models": { "total": 0.02745988400056376, "count": 1, "self": 0.00041665999742690474, "children": { "RLTrainer._checkpoint": { "total": 0.027043224003136856, "count": 1, "self": 0.027043224003136856 } } } } } } }