{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5663065910339355, "min": 0.5663065910339355, "max": 1.4268097877502441, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17070.74609375, "min": 17002.728515625, "max": 43283.703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6015336513519287, "min": -0.09212841838598251, "max": 0.6015336513519287, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 170.23402404785156, "min": -22.110820770263672, "max": 170.23402404785156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.01211459655314684, "min": -0.18527160584926605, "max": 0.3338637351989746, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.4284307956695557, "min": -49.28224563598633, "max": 80.4611587524414, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06800913653528533, "min": 0.06423389322274588, "max": 0.07203922373721272, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9521279114939947, "min": 0.4833972406223679, "max": 1.0805883560581908, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016080190909567294, "min": 0.0003193308213101466, "max": 0.016080190909567294, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2251226727339421, "min": 0.004151300677031906, "max": 0.2251226727339421, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.586518899764285e-06, "min": 7.586518899764285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010621126459669998, "min": 0.00010621126459669998, "max": 0.0036092583969138995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252880714285714, "min": 0.10252880714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354033, "min": 1.3886848, "max": 2.5266878, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002626278335714285, "min": 0.0002626278335714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036767896699999992, "min": 0.0036767896699999992, "max": 0.12031830139, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012014316394925117, "min": 0.010946983471512794, "max": 0.4582044184207916, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16820043325424194, "min": 0.15325777232646942, "max": 3.207430839538574, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 314.6808510638298, "min": 314.6808510638298, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29580.0, "min": 15984.0, "max": 33429.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.64275316925759, "min": -1.0000000521540642, "max": 1.64275316925759, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 154.41879791021347, "min": -30.996801614761353, "max": 154.41879791021347, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.64275316925759, "min": -1.0000000521540642, "max": 1.64275316925759, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 154.41879791021347, "min": -30.996801614761353, "max": 154.41879791021347, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03951169153376039, "min": 0.039277552386520656, "max": 8.452160771936178, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7140990041734767, "min": 3.240190844546305, "max": 135.23457235097885, "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": "1729746868", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729749159" }, "total": 2291.6681479599997, "count": 1, "self": 0.4885614960003295, "children": { "run_training.setup": { "total": 0.05333554499975435, "count": 1, "self": 0.05333554499975435 }, "TrainerController.start_learning": { "total": 2291.1262509189996, "count": 1, "self": 1.4343274919419855, "children": { "TrainerController._reset_env": { "total": 3.0388356930002374, "count": 1, "self": 3.0388356930002374 }, "TrainerController.advance": { "total": 2286.5670519810574, "count": 63878, "self": 1.5052468551243692, "children": { "env_step": { "total": 1586.9899723979265, "count": 63878, "self": 1431.470810495794, "children": { "SubprocessEnvManager._take_step": { "total": 154.65159140106243, "count": 63878, "self": 4.837448747128747, "children": { "TorchPolicy.evaluate": { "total": 149.8141426539337, "count": 62563, "self": 149.8141426539337 } } }, "workers": { "total": 0.8675705010700767, "count": 63878, "self": 0.0, "children": { "worker_root": { "total": 2285.9102573059185, "count": 63878, "is_parallel": true, "self": 977.2627648039402, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002880645999994158, "count": 1, "is_parallel": true, "self": 0.0008352440004273376, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020454019995668205, "count": 8, "is_parallel": true, "self": 0.0020454019995668205 } } }, "UnityEnvironment.step": { "total": 0.10059841500014954, "count": 1, "is_parallel": true, "self": 0.0006338210005196743, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004842379998990509, "count": 1, "is_parallel": true, "self": 0.0004842379998990509 }, "communicator.exchange": { "total": 0.09765584899969326, "count": 1, "is_parallel": true, "self": 0.09765584899969326 }, "steps_from_proto": { "total": 0.0018245070000375563, "count": 1, "is_parallel": true, "self": 0.0003872679999403772, "children": { "_process_rank_one_or_two_observation": { "total": 0.001437239000097179, "count": 8, "is_parallel": true, "self": 0.001437239000097179 } } } } } } }, "UnityEnvironment.step": { "total": 1308.6474925019784, "count": 63877, "is_parallel": true, "self": 33.97404751390695, "children": { "UnityEnvironment._generate_step_input": { "total": 23.638577762112163, "count": 63877, "is_parallel": true, "self": 23.638577762112163 }, "communicator.exchange": { "total": 1149.2144369129046, "count": 63877, "is_parallel": true, "self": 1149.2144369129046 }, "steps_from_proto": { "total": 101.82043031305466, "count": 63877, "is_parallel": true, "self": 21.004531856867743, "children": { "_process_rank_one_or_two_observation": { "total": 80.81589845618691, "count": 511016, "is_parallel": true, "self": 80.81589845618691 } } } } } } } } } } }, "trainer_advance": { "total": 698.0718327280065, "count": 63878, "self": 2.6852551830270386, "children": { "process_trajectory": { "total": 141.27932785798248, "count": 63878, "self": 141.06389039298256, "children": { "RLTrainer._checkpoint": { "total": 0.21543746499992267, "count": 2, "self": 0.21543746499992267 } } }, "_update_policy": { "total": 554.107249686997, "count": 456, "self": 310.1857977609998, "children": { "TorchPPOOptimizer.update": { "total": 243.9214519259972, "count": 22770, "self": 243.9214519259972 } } } } } } }, "trainer_threads": { "total": 1.1160000212839805e-06, "count": 1, "self": 1.1160000212839805e-06 }, "TrainerController._save_models": { "total": 0.08603463700001157, "count": 1, "self": 0.0015955369999574032, "children": { "RLTrainer._checkpoint": { "total": 0.08443910000005417, "count": 1, "self": 0.08443910000005417 } } } } } } }