{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5159269571304321, "min": 0.5129492878913879, "max": 1.448936939239502, "count": 23 }, "Pyramids.Policy.Entropy.sum": { "value": 15477.80859375, "min": 15232.5419921875, "max": 43954.94921875, "count": 23 }, "Pyramids.Step.mean": { "value": 689998.0, "min": 29996.0, "max": 689998.0, "count": 23 }, "Pyramids.Step.sum": { "value": 689998.0, "min": 29996.0, "max": 689998.0, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44156432151794434, "min": -0.0628989040851593, "max": 0.47608819603919983, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.89767456054688, "min": -15.158636093139648, "max": 129.0198974609375, "count": 23 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03201933205127716, "min": -0.0577508769929409, "max": 0.3878459632396698, "count": 23 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.549161911010742, "min": -15.592737197875977, "max": 92.30734252929688, "count": 23 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06585418448126543, "min": 0.06469609509942875, "max": 0.07125436491927928, "count": 23 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9219585827377159, "min": 0.49878055443495495, "max": 1.0394744463578807, "count": 23 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01466034116899772, "min": 0.0010189180087605602, "max": 0.016069453655550854, "count": 23 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20524477636596808, "min": 0.013245934113887282, "max": 0.22497235117771197, "count": 23 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.0952851451122447e-05, "min": 1.0952851451122447e-05, "max": 0.0002931950226764897, "count": 23 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00015333992031571427, "min": 0.00015333992031571427, "max": 0.003484989138337, "count": 23 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10365091836734694, "min": 0.10365091836734694, "max": 0.19773167346938775, "count": 23 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.451112857142857, "min": 1.3841217142857143, "max": 2.5318924285714286, "count": 23 }, "Pyramids.Policy.Beta.mean": { "value": 0.00037472674489795916, "min": 0.00037472674489795916, "max": 0.009773394179591836, "count": 23 }, "Pyramids.Policy.Beta.sum": { "value": 0.0052461744285714285, "min": 0.0052461744285714285, "max": 0.11618013370000001, "count": 23 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01385729480534792, "min": 0.01385729480534792, "max": 0.46793070435523987, "count": 23 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19400212168693542, "min": 0.19400212168693542, "max": 3.275514841079712, "count": 23 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 418.07042253521126, "min": 388.71794871794873, "max": 980.4117647058823, "count": 23 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29683.0, "min": 16667.0, "max": 34018.0, "count": 23 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3565182829616775, "min": -0.8637059322174858, "max": 1.5475211074234734, "count": 23 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 96.3127980902791, "min": -28.119801722466946, "max": 117.67699871957302, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3565182829616775, "min": -0.8637059322174858, "max": 1.5475211074234734, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 96.3127980902791, "min": -28.119801722466946, "max": 117.67699871957302, "count": 23 }, "Pyramids.Policy.RndReward.mean": { "value": 0.060279124154271495, "min": 0.05957469614825218, "max": 9.228095879449564, "count": 23 }, "Pyramids.Policy.RndReward.sum": { "value": 4.279817814953276, "min": 4.229803426525905, "max": 156.87762995064259, "count": 23 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719674461", "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 Training1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719676062" }, "total": 1600.8617605089999, "count": 1, "self": 0.4436223229997722, "children": { "run_training.setup": { "total": 0.08845487799999319, "count": 1, "self": 0.08845487799999319 }, "TrainerController.start_learning": { "total": 1600.329683308, "count": 1, "self": 1.1158604610075145, "children": { "TrainerController._reset_env": { "total": 3.7024018749998504, "count": 1, "self": 3.7024018749998504 }, "TrainerController.advance": { "total": 1595.4237527419932, "count": 44597, "self": 1.1494493289567345, "children": { "env_step": { "total": 1138.7097346640203, "count": 44597, "self": 1035.230790629002, "children": { "SubprocessEnvManager._take_step": { "total": 102.78661415901774, "count": 44597, "self": 3.440552423020563, "children": { "TorchPolicy.evaluate": { "total": 99.34606173599718, "count": 43803, "self": 99.34606173599718 } } }, "workers": { "total": 0.6923298760004855, "count": 44597, "self": 0.0, "children": { "worker_root": { "total": 1596.4229978130404, "count": 44597, "is_parallel": true, "self": 654.8639752220511, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.015612085000157094, "count": 1, "is_parallel": true, "self": 0.004930926000042746, "children": { "_process_rank_one_or_two_observation": { "total": 0.010681159000114349, "count": 8, "is_parallel": true, "self": 0.010681159000114349 } } }, "UnityEnvironment.step": { "total": 0.046516110000084154, "count": 1, "is_parallel": true, "self": 0.0006918040000982728, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004822470000362955, "count": 1, "is_parallel": true, "self": 0.0004822470000362955 }, "communicator.exchange": { "total": 0.043688985000017055, "count": 1, "is_parallel": true, "self": 0.043688985000017055 }, "steps_from_proto": { "total": 0.0016530739999325306, "count": 1, "is_parallel": true, "self": 0.000369832999922437, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012832410000100936, "count": 8, "is_parallel": true, "self": 0.0012832410000100936 } } } } } } }, "UnityEnvironment.step": { "total": 941.5590225909893, "count": 44596, "is_parallel": true, "self": 25.116252618046474, "children": { "UnityEnvironment._generate_step_input": { "total": 16.57159033200537, "count": 44596, "is_parallel": true, "self": 16.57159033200537 }, "communicator.exchange": { "total": 829.7306253509655, "count": 44596, "is_parallel": true, "self": 829.7306253509655 }, "steps_from_proto": { "total": 70.14055428997199, "count": 44596, "is_parallel": true, "self": 14.835980148910494, "children": { "_process_rank_one_or_two_observation": { "total": 55.304574141061494, "count": 356768, "is_parallel": true, "self": 55.304574141061494 } } } } } } } } } } }, "trainer_advance": { "total": 455.5645687490162, "count": 44597, "self": 2.199988050052525, "children": { "process_trajectory": { "total": 90.09018176896029, "count": 44597, "self": 89.90162720396052, "children": { "RLTrainer._checkpoint": { "total": 0.18855456499977663, "count": 1, "self": 0.18855456499977663 } } }, "_update_policy": { "total": 363.2743989300034, "count": 318, "self": 216.69494764799947, "children": { "TorchPPOOptimizer.update": { "total": 146.5794512820039, "count": 15948, "self": 146.5794512820039 } } } } } } }, "trainer_threads": { "total": 9.7599968285067e-07, "count": 1, "self": 9.7599968285067e-07 }, "TrainerController._save_models": { "total": 0.08766725399982533, "count": 1, "self": 0.001347486999748071, "children": { "RLTrainer._checkpoint": { "total": 0.08631976700007726, "count": 1, "self": 0.08631976700007726 } } } } } } }