{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5753702521324158, "min": 0.5753702521324158, "max": 1.4426660537719727, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17196.666015625, "min": 17196.666015625, "max": 43764.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40613117814064026, "min": -0.15026439726352692, "max": 0.45144471526145935, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.03089141845703, "min": -35.61266326904297, "max": 119.63285064697266, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.009124238044023514, "min": -0.029045553877949715, "max": 0.4384632408618927, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.4270472526550293, "min": -7.580889701843262, "max": 103.91578674316406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.067655319017319, "min": 0.06487469409242877, "max": 0.07474114674027652, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9471744662424659, "min": 0.5231880271819356, "max": 1.0233216122929556, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016190533736673885, "min": 0.00019880942596791793, "max": 0.016190533736673885, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2266674723134344, "min": 0.002584522537582933, "max": 0.2266674723134344, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.739411705942855e-06, "min": 7.739411705942855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010835176388319997, "min": 0.00010835176388319997, "max": 0.0036324049891983995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257977142857143, "min": 0.10257977142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361168, "min": 1.3886848, "max": 2.6108016000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002677191657142857, "min": 0.0002677191657142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037480683199999994, "min": 0.0037480683199999994, "max": 0.12109907984, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012992961332201958, "min": 0.012440472841262817, "max": 0.5060054063796997, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1819014549255371, "min": 0.17416661977767944, "max": 3.5420379638671875, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 443.8235294117647, "min": 430.6811594202899, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30180.0, "min": 15984.0, "max": 32798.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4720869349396748, "min": -1.0000000521540642, "max": 1.4720869349396748, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 101.57399851083755, "min": -28.30140160769224, "max": 101.57399851083755, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4720869349396748, "min": -1.0000000521540642, "max": 1.4720869349396748, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 101.57399851083755, "min": -28.30140160769224, "max": 101.57399851083755, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05971444080173767, "min": 0.05739739864679216, "max": 10.715156993828714, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.120296415319899, "min": 3.7882283106882824, "max": 171.44251190125942, "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": "1692603496", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/ml2/anaconda3/envs/huggingface/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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692604894" }, "total": 1397.3712858830113, "count": 1, "self": 0.2696390420314856, "children": { "run_training.setup": { "total": 0.014146807952784002, "count": 1, "self": 0.014146807952784002 }, "TrainerController.start_learning": { "total": 1397.087500033027, "count": 1, "self": 1.2207513459725305, "children": { "TrainerController._reset_env": { "total": 3.931215503020212, "count": 1, "self": 3.931215503020212 }, "TrainerController.advance": { "total": 1391.8571872240864, "count": 63521, "self": 1.151954012166243, "children": { "env_step": { "total": 907.7625118871802, "count": 63521, "self": 811.6470469153719, "children": { "SubprocessEnvManager._take_step": { "total": 95.32783755863784, "count": 63521, "self": 3.599782832839992, "children": { "TorchPolicy.evaluate": { "total": 91.72805472579785, "count": 62558, "self": 91.72805472579785 } } }, "workers": { "total": 0.7876274131704122, "count": 63521, "self": 0.0, "children": { "worker_root": { "total": 1395.1051624785177, "count": 63521, "is_parallel": true, "self": 669.1663743341342, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011529979528859258, "count": 1, "is_parallel": true, "self": 0.0003218860365450382, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008311119163408875, "count": 8, "is_parallel": true, "self": 0.0008311119163408875 } } }, "UnityEnvironment.step": { "total": 0.03720399102894589, "count": 1, "is_parallel": true, "self": 0.0006220769137144089, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020581204444169998, "count": 1, "is_parallel": true, "self": 0.00020581204444169998 }, "communicator.exchange": { "total": 0.03521048603579402, "count": 1, "is_parallel": true, "self": 0.03521048603579402 }, "steps_from_proto": { "total": 0.0011656160349957645, "count": 1, "is_parallel": true, "self": 0.00023042107932269573, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009351949556730688, "count": 8, "is_parallel": true, "self": 0.0009351949556730688 } } } } } } }, "UnityEnvironment.step": { "total": 725.9387881443836, "count": 63520, "is_parallel": true, "self": 24.92760451254435, "children": { "UnityEnvironment._generate_step_input": { "total": 15.41701837774599, "count": 63520, "is_parallel": true, "self": 15.41701837774599 }, "communicator.exchange": { "total": 617.5892663678969, "count": 63520, "is_parallel": true, "self": 617.5892663678969 }, "steps_from_proto": { "total": 68.00489888619632, "count": 63520, "is_parallel": true, "self": 13.149956691544503, "children": { "_process_rank_one_or_two_observation": { "total": 54.85494219465181, "count": 508160, "is_parallel": true, "self": 54.85494219465181 } } } } } } } } } } }, "trainer_advance": { "total": 482.94272132474, "count": 63521, "self": 2.285724444547668, "children": { "process_trajectory": { "total": 79.77023568394361, "count": 63521, "self": 79.60781575995497, "children": { "RLTrainer._checkpoint": { "total": 0.16241992398863658, "count": 2, "self": 0.16241992398863658 } } }, "_update_policy": { "total": 400.8867611962487, "count": 453, "self": 251.70911804697243, "children": { "TorchPPOOptimizer.update": { "total": 149.17764314927626, "count": 22776, "self": 149.17764314927626 } } } } } } }, "trainer_threads": { "total": 6.789923645555973e-07, "count": 1, "self": 6.789923645555973e-07 }, "TrainerController._save_models": { "total": 0.0783452809555456, "count": 1, "self": 0.0010301759466528893, "children": { "RLTrainer._checkpoint": { "total": 0.07731510500889271, "count": 1, "self": 0.07731510500889271 } } } } } } }