{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4559151828289032, "min": 0.4422323703765869, "max": 1.4052366018295288, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13582.625, "min": 13274.046875, "max": 42629.2578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48993533849716187, "min": -0.11382244527339935, "max": 0.511127233505249, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 134.24227905273438, "min": -27.431209564208984, "max": 141.0711212158203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.029282841831445694, "min": 0.029282841831445694, "max": 0.5828818082809448, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.02349853515625, "min": 8.02349853515625, "max": 139.89163208007812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06744790576132281, "min": 0.06498703005743546, "max": 0.07305000646628279, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9442706806585194, "min": 0.488342339750018, "max": 1.0373851726608871, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014664451570189113, "min": 0.0011588689386030318, "max": 0.015088778200653656, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20530232198264758, "min": 0.012988580887551882, "max": 0.21130263393085139, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.525597491499999e-06, "min": 7.525597491499999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010535836488099998, "min": 0.00010535836488099998, "max": 0.003633921488692899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250849999999999, "min": 0.10250849999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351189999999998, "min": 1.3691136000000002, "max": 2.6113071, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026059915000000003, "min": 0.00026059915000000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036483881000000007, "min": 0.0036483881000000007, "max": 0.12114957929, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016887223348021507, "min": 0.016887223348021507, "max": 0.4436214566230774, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.236421138048172, "min": 0.236421138048172, "max": 3.1053502559661865, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 376.775, "min": 376.2470588235294, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30142.0, "min": 15984.0, "max": 32920.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5414419560520738, "min": -1.0000000521540642, "max": 1.5766776216380736, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.85679844021797, "min": -32.000001668930054, "max": 134.01759783923626, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5414419560520738, "min": -1.0000000521540642, "max": 1.5766776216380736, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.85679844021797, "min": -32.000001668930054, "max": 134.01759783923626, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.13358603501448085, "min": 0.13358603501448085, "max": 15.834431545808911, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 10.82046883617295, "min": 9.927237732510548, "max": 253.35090473294258, "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": "1681647204", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681649600" }, "total": 2396.1113926949997, "count": 1, "self": 0.909659716999613, "children": { "run_training.setup": { "total": 0.11602401300001475, "count": 1, "self": 0.11602401300001475 }, "TrainerController.start_learning": { "total": 2395.085708965, "count": 1, "self": 1.996679792026498, "children": { "TrainerController._reset_env": { "total": 4.098378780999951, "count": 1, "self": 4.098378780999951 }, "TrainerController.advance": { "total": 2388.830204293973, "count": 63738, "self": 2.0129098109368897, "children": { "env_step": { "total": 1743.9614275100366, "count": 63738, "self": 1605.7994242030586, "children": { "SubprocessEnvManager._take_step": { "total": 136.91944303600337, "count": 63738, "self": 5.6998883750188725, "children": { "TorchPolicy.evaluate": { "total": 131.2195546609845, "count": 62569, "self": 131.2195546609845 } } }, "workers": { "total": 1.2425602709747636, "count": 63738, "self": 0.0, "children": { "worker_root": { "total": 2388.6352776790027, "count": 63738, "is_parallel": true, "self": 921.8071001679627, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006126612000002751, "count": 1, "is_parallel": true, "self": 0.004685610000251472, "children": { "_process_rank_one_or_two_observation": { "total": 0.001441001999751279, "count": 8, "is_parallel": true, "self": 0.001441001999751279 } } }, "UnityEnvironment.step": { "total": 0.051761601999942286, "count": 1, "is_parallel": true, "self": 0.0006463089998760552, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005826740000429709, "count": 1, "is_parallel": true, "self": 0.0005826740000429709 }, "communicator.exchange": { "total": 0.048374417999980324, "count": 1, "is_parallel": true, "self": 0.048374417999980324 }, "steps_from_proto": { "total": 0.0021582010000429364, "count": 1, "is_parallel": true, "self": 0.0005100459999312079, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016481550001117284, "count": 8, "is_parallel": true, "self": 0.0016481550001117284 } } } } } } }, "UnityEnvironment.step": { "total": 1466.82817751104, "count": 63737, "is_parallel": true, "self": 36.63106474803635, "children": { "UnityEnvironment._generate_step_input": { "total": 26.225539284004867, "count": 63737, "is_parallel": true, "self": 26.225539284004867 }, "communicator.exchange": { "total": 1293.5296550399603, "count": 63737, "is_parallel": true, "self": 1293.5296550399603 }, "steps_from_proto": { "total": 110.44191843903843, "count": 63737, "is_parallel": true, "self": 24.89603632997739, "children": { "_process_rank_one_or_two_observation": { "total": 85.54588210906104, "count": 509896, "is_parallel": true, "self": 85.54588210906104 } } } } } } } } } } }, "trainer_advance": { "total": 642.8558669729996, "count": 63738, "self": 3.6148124689850647, "children": { "process_trajectory": { "total": 118.86801613701584, "count": 63738, "self": 118.53411737401541, "children": { "RLTrainer._checkpoint": { "total": 0.333898763000434, "count": 2, "self": 0.333898763000434 } } }, "_update_policy": { "total": 520.3730383669987, "count": 450, "self": 331.7025403050093, "children": { "TorchPPOOptimizer.update": { "total": 188.6704980619894, "count": 22770, "self": 188.6704980619894 } } } } } } }, "trainer_threads": { "total": 1.3459998626785818e-06, "count": 1, "self": 1.3459998626785818e-06 }, "TrainerController._save_models": { "total": 0.16044475200033048, "count": 1, "self": 0.0020525010004348587, "children": { "RLTrainer._checkpoint": { "total": 0.15839225099989562, "count": 1, "self": 0.15839225099989562 } } } } } } }