{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3815002143383026, "min": 0.355610191822052, "max": 1.4727157354354858, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11493.8388671875, "min": 10651.236328125, "max": 44676.3046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5834378004074097, "min": -0.1707555055618286, "max": 0.6622437238693237, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 163.94601440429688, "min": -40.46905517578125, "max": 192.71292114257812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06509080529212952, "min": -0.2689429223537445, "max": 0.45066505670547485, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.290515899658203, "min": -76.37979125976562, "max": 106.8076171875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07032672611586306, "min": 0.06621863313124604, "max": 0.0733547788418253, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9845741656220829, "min": 0.47239429945354994, "max": 1.070762459896893, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.027843490233256794, "min": 0.0014670771499081241, "max": 0.027843490233256794, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3898088632655951, "min": 0.010625317061311207, "max": 0.3898088632655951, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.395611820542856e-06, "min": 7.395611820542856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010353856548759998, "min": 0.00010353856548759998, "max": 0.0032584958138348, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246517142857146, "min": 0.10246517142857146, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345124000000005, "min": 1.3691136000000002, "max": 2.4858198, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025627062571428573, "min": 0.00025627062571428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00358778876, "min": 0.00358778876, "max": 0.10863790348, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008785853162407875, "min": 0.008579774759709835, "max": 0.42506569623947144, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12300194054841995, "min": 0.12300194054841995, "max": 2.9754598140716553, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.29347826086956, "min": 282.05555555555554, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30295.0, "min": 15984.0, "max": 33981.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5837260670150104, "min": -1.0000000521540642, "max": 1.6994166529426973, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.70279816538095, "min": -32.000001668930054, "max": 183.5369985178113, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5837260670150104, "min": -1.0000000521540642, "max": 1.6994166529426973, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.70279816538095, "min": -32.000001668930054, "max": 183.5369985178113, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02960676156647463, "min": 0.026308634459520832, "max": 8.492122150957584, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.723822064115666, "min": 2.6045548114925623, "max": 135.87395441532135, "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": "1696710169", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696712563" }, "total": 2393.969678263, "count": 1, "self": 0.47550651299934543, "children": { "run_training.setup": { "total": 0.042267687000276055, "count": 1, "self": 0.042267687000276055 }, "TrainerController.start_learning": { "total": 2393.4519040630003, "count": 1, "self": 1.5517238758338863, "children": { "TrainerController._reset_env": { "total": 3.0201437169998826, "count": 1, "self": 3.0201437169998826 }, "TrainerController.advance": { "total": 2388.798853809166, "count": 63908, "self": 1.567956991027586, "children": { "env_step": { "total": 1648.7635433490827, "count": 63908, "self": 1513.8643645580232, "children": { "SubprocessEnvManager._take_step": { "total": 133.98884237199718, "count": 63908, "self": 5.042947454931891, "children": { "TorchPolicy.evaluate": { "total": 128.9458949170653, "count": 62564, "self": 128.9458949170653 } } }, "workers": { "total": 0.9103364190623324, "count": 63908, "self": 0.0, "children": { "worker_root": { "total": 2388.293373693879, "count": 63908, "is_parallel": true, "self": 1002.9505098629011, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002011757999753172, "count": 1, "is_parallel": true, "self": 0.0006104760000198439, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014012819997333281, "count": 8, "is_parallel": true, "self": 0.0014012819997333281 } } }, "UnityEnvironment.step": { "total": 0.053637976000118215, "count": 1, "is_parallel": true, "self": 0.0005762670007243287, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005297349998727441, "count": 1, "is_parallel": true, "self": 0.0005297349998727441 }, "communicator.exchange": { "total": 0.04987142199979644, "count": 1, "is_parallel": true, "self": 0.04987142199979644 }, "steps_from_proto": { "total": 0.002660551999724703, "count": 1, "is_parallel": true, "self": 0.0004953649995513842, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021651870001733187, "count": 8, "is_parallel": true, "self": 0.0021651870001733187 } } } } } } }, "UnityEnvironment.step": { "total": 1385.3428638309779, "count": 63907, "is_parallel": true, "self": 35.29512878188598, "children": { "UnityEnvironment._generate_step_input": { "total": 25.77566102695164, "count": 63907, "is_parallel": true, "self": 25.77566102695164 }, "communicator.exchange": { "total": 1208.8517999500955, "count": 63907, "is_parallel": true, "self": 1208.8517999500955 }, "steps_from_proto": { "total": 115.42027407204478, "count": 63907, "is_parallel": true, "self": 23.085294917598276, "children": { "_process_rank_one_or_two_observation": { "total": 92.3349791544465, "count": 511256, "is_parallel": true, "self": 92.3349791544465 } } } } } } } } } } }, "trainer_advance": { "total": 738.4673534690555, "count": 63908, "self": 2.7380072531336737, "children": { "process_trajectory": { "total": 132.91661907591742, "count": 63908, "self": 132.7303127519176, "children": { "RLTrainer._checkpoint": { "total": 0.1863063239998155, "count": 2, "self": 0.1863063239998155 } } }, "_update_policy": { "total": 602.8127271400044, "count": 445, "self": 390.61249259602846, "children": { "TorchPPOOptimizer.update": { "total": 212.20023454397597, "count": 22857, "self": 212.20023454397597 } } } } } } }, "trainer_threads": { "total": 9.920004231389612e-07, "count": 1, "self": 9.920004231389612e-07 }, "TrainerController._save_models": { "total": 0.08118166900021606, "count": 1, "self": 0.0014543070001309388, "children": { "RLTrainer._checkpoint": { "total": 0.07972736200008512, "count": 1, "self": 0.07972736200008512 } } } } } } }