{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2947995662689209, "min": 0.2947995662689209, "max": 1.4569668769836426, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8777.9521484375, "min": 8777.9521484375, "max": 44198.546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38858091831207275, "min": -0.10287878662347794, "max": 0.458749383687973, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 104.13968658447266, "min": -24.793787002563477, "max": 125.7011489868164, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0031999957282096148, "min": 0.0031999957282096148, "max": 0.35867226123809814, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8575988411903381, "min": 0.8575988411903381, "max": 86.08134460449219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07214684136644274, "min": 0.06638876214782911, "max": 0.07359967636481989, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0100557791301983, "min": 0.49122007660906974, "max": 1.0718772829680712, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013351166448642713, "min": 0.0002453727416938922, "max": 0.013795532955231867, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18691633028099797, "min": 0.002944472900326707, "max": 0.206932994328478, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.402854675271429e-06, "min": 7.402854675271429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010363996545380001, "min": 0.00010363996545380001, "max": 0.0032229733256755994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246758571428571, "min": 0.10246758571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345462, "min": 1.3691136000000002, "max": 2.4004599, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002565118128571429, "min": 0.0002565118128571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035911653800000005, "min": 0.0035911653800000005, "max": 0.10744500756, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01698884554207325, "min": 0.01698884554207325, "max": 0.41666680574417114, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2378438264131546, "min": 0.2378438264131546, "max": 2.9166676998138428, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 435.463768115942, "min": 395.76, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30047.0, "min": 15984.0, "max": 33322.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4195622998303261, "min": -1.0000000521540642, "max": 1.5242106546958287, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 97.9497986882925, "min": -32.000001668930054, "max": 114.31579910218716, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4195622998303261, "min": -1.0000000521540642, "max": 1.5242106546958287, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 97.9497986882925, "min": -32.000001668930054, "max": 114.31579910218716, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0772763813020783, "min": 0.07053934471468286, "max": 7.403217487037182, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.332070309843402, "min": 5.05967963533476, "max": 118.45147979259491, "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": "1718079904", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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 Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718082162" }, "total": 2257.62948341, "count": 1, "self": 1.0424122399995213, "children": { "run_training.setup": { "total": 0.05394010800000615, "count": 1, "self": 0.05394010800000615 }, "TrainerController.start_learning": { "total": 2256.5331310620004, "count": 1, "self": 1.6712503580733937, "children": { "TrainerController._reset_env": { "total": 3.0052795520000473, "count": 1, "self": 3.0052795520000473 }, "TrainerController.advance": { "total": 2251.722645144927, "count": 63543, "self": 1.6869991938078783, "children": { "env_step": { "total": 1599.1887181640698, "count": 63543, "self": 1446.5715793320405, "children": { "SubprocessEnvManager._take_step": { "total": 151.5694673970204, "count": 63543, "self": 5.253002247975928, "children": { "TorchPolicy.evaluate": { "total": 146.31646514904446, "count": 62569, "self": 146.31646514904446 } } }, "workers": { "total": 1.0476714350088514, "count": 63543, "self": 0.0, "children": { "worker_root": { "total": 2250.5153105218983, "count": 63543, "is_parallel": true, "self": 942.5517317298415, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00337116699984108, "count": 1, "is_parallel": true, "self": 0.0008562140001231455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025149529997179343, "count": 8, "is_parallel": true, "self": 0.0025149529997179343 } } }, "UnityEnvironment.step": { "total": 0.07360094199998457, "count": 1, "is_parallel": true, "self": 0.000693913000077373, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004570730000068579, "count": 1, "is_parallel": true, "self": 0.0004570730000068579 }, "communicator.exchange": { "total": 0.07082705199991324, "count": 1, "is_parallel": true, "self": 0.07082705199991324 }, "steps_from_proto": { "total": 0.001622903999987102, "count": 1, "is_parallel": true, "self": 0.00034770499974001723, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012751990002470848, "count": 8, "is_parallel": true, "self": 0.0012751990002470848 } } } } } } }, "UnityEnvironment.step": { "total": 1307.9635787920568, "count": 63542, "is_parallel": true, "self": 36.602386062954565, "children": { "UnityEnvironment._generate_step_input": { "total": 23.97292827801698, "count": 63542, "is_parallel": true, "self": 23.97292827801698 }, "communicator.exchange": { "total": 1145.0359597780484, "count": 63542, "is_parallel": true, "self": 1145.0359597780484 }, "steps_from_proto": { "total": 102.35230467303677, "count": 63542, "is_parallel": true, "self": 21.554313037069278, "children": { "_process_rank_one_or_two_observation": { "total": 80.79799163596749, "count": 508336, "is_parallel": true, "self": 80.79799163596749 } } } } } } } } } } }, "trainer_advance": { "total": 650.8469277870493, "count": 63543, "self": 3.031774161911926, "children": { "process_trajectory": { "total": 130.6781311691334, "count": 63543, "self": 130.35591404913293, "children": { "RLTrainer._checkpoint": { "total": 0.32221712000045954, "count": 2, "self": 0.32221712000045954 } } }, "_update_policy": { "total": 517.1370224560039, "count": 440, "self": 305.0142634409988, "children": { "TorchPPOOptimizer.update": { "total": 212.12275901500516, "count": 22845, "self": 212.12275901500516 } } } } } } }, "trainer_threads": { "total": 1.3250000847619958e-06, "count": 1, "self": 1.3250000847619958e-06 }, "TrainerController._save_models": { "total": 0.13395468199996685, "count": 1, "self": 0.0020337500000096043, "children": { "RLTrainer._checkpoint": { "total": 0.13192093199995725, "count": 1, "self": 0.13192093199995725 } } } } } } }