{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.298994779586792, "min": 0.298994779586792, "max": 1.455559492111206, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8922.00390625, "min": 8922.00390625, "max": 44155.8515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5951288342475891, "min": -0.10273827612400055, "max": 0.5951288342475891, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.82632446289062, "min": -24.759923934936523, "max": 167.82632446289062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027363643050193787, "min": -0.04839562252163887, "max": 0.270280659198761, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.71654748916626, "min": -13.453983306884766, "max": 64.86735534667969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0709976014512081, "min": 0.062307845604154664, "max": 0.0736954469898248, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9939664203169134, "min": 0.5032895741925372, "max": 1.0404911754206598, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016221521657869397, "min": 0.0011163409301227691, "max": 0.017868304395233285, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22710130321017158, "min": 0.008696662315742287, "max": 0.26802456592849927, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3354618405928595e-06, "min": 7.3354618405928595e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010269646576830003, "min": 0.00010269646576830003, "max": 0.0032577102140967, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244512142857144, "min": 0.10244512142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342317000000002, "min": 1.3691136000000002, "max": 2.5274766, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002542676307142858, "min": 0.0002542676307142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003559746830000001, "min": 0.003559746830000001, "max": 0.10862173967, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009958148002624512, "min": 0.009958148002624512, "max": 0.43389567732810974, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13941407203674316, "min": 0.13941407203674316, "max": 3.0372698307037354, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 321.6304347826087, "min": 316.4639175257732, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29590.0, "min": 15984.0, "max": 32402.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6551208641011637, "min": -1.0000000521540642, "max": 1.6551208641011637, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.6159986332059, "min": -32.000001668930054, "max": 160.8313976302743, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6551208641011637, "min": -1.0000000521540642, "max": 1.6551208641011637, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.6159986332059, "min": -32.000001668930054, "max": 160.8313976302743, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0334390595946768, "min": 0.0334390595946768, "max": 9.24591356702149, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0429544231155887, "min": 3.0429544231155887, "max": 147.93461707234383, "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": "1702844952", "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 Training --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702847109" }, "total": 2157.511885796, "count": 1, "self": 0.4768154900002628, "children": { "run_training.setup": { "total": 0.04586315000005925, "count": 1, "self": 0.04586315000005925 }, "TrainerController.start_learning": { "total": 2156.989207156, "count": 1, "self": 1.355790103938034, "children": { "TrainerController._reset_env": { "total": 1.9440357630001017, "count": 1, "self": 1.9440357630001017 }, "TrainerController.advance": { "total": 2153.6007212040618, "count": 63896, "self": 1.4014022630740328, "children": { "env_step": { "total": 1525.1982764899913, "count": 63896, "self": 1394.740882413091, "children": { "SubprocessEnvManager._take_step": { "total": 129.61764575391294, "count": 63896, "self": 4.686751131872597, "children": { "TorchPolicy.evaluate": { "total": 124.93089462204034, "count": 62552, "self": 124.93089462204034 } } }, "workers": { "total": 0.8397483229873615, "count": 63896, "self": 0.0, "children": { "worker_root": { "total": 2151.888454610957, "count": 63896, "is_parallel": true, "self": 877.9743223220098, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001664329000050202, "count": 1, "is_parallel": true, "self": 0.0005204060000778554, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011439229999723466, "count": 8, "is_parallel": true, "self": 0.0011439229999723466 } } }, "UnityEnvironment.step": { "total": 0.05296441700011201, "count": 1, "is_parallel": true, "self": 0.0005742160003592289, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005029469998589775, "count": 1, "is_parallel": true, "self": 0.0005029469998589775 }, "communicator.exchange": { "total": 0.050216353999985586, "count": 1, "is_parallel": true, "self": 0.050216353999985586 }, "steps_from_proto": { "total": 0.0016708999999082152, "count": 1, "is_parallel": true, "self": 0.00039878699931250594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012721130005957093, "count": 8, "is_parallel": true, "self": 0.0012721130005957093 } } } } } } }, "UnityEnvironment.step": { "total": 1273.9141322889473, "count": 63895, "is_parallel": true, "self": 34.933429909751794, "children": { "UnityEnvironment._generate_step_input": { "total": 24.83320170505999, "count": 63895, "is_parallel": true, "self": 24.83320170505999 }, "communicator.exchange": { "total": 1113.516335700075, "count": 63895, "is_parallel": true, "self": 1113.516335700075 }, "steps_from_proto": { "total": 100.63116497406054, "count": 63895, "is_parallel": true, "self": 20.2012589581434, "children": { "_process_rank_one_or_two_observation": { "total": 80.42990601591714, "count": 511160, "is_parallel": true, "self": 80.42990601591714 } } } } } } } } } } }, "trainer_advance": { "total": 627.0010424509962, "count": 63896, "self": 2.655270620972942, "children": { "process_trajectory": { "total": 126.98859662802192, "count": 63896, "self": 126.79614209402212, "children": { "RLTrainer._checkpoint": { "total": 0.1924545339998076, "count": 2, "self": 0.1924545339998076 } } }, "_update_policy": { "total": 497.3571752020014, "count": 447, "self": 297.6529673510213, "children": { "TorchPPOOptimizer.update": { "total": 199.70420785098008, "count": 22821, "self": 199.70420785098008 } } } } } } }, "trainer_threads": { "total": 8.71000338520389e-07, "count": 1, "self": 8.71000338520389e-07 }, "TrainerController._save_models": { "total": 0.08865921399956278, "count": 1, "self": 0.0018681449992072885, "children": { "RLTrainer._checkpoint": { "total": 0.08679106900035549, "count": 1, "self": 0.08679106900035549 } } } } } } }