{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41876494884490967, "min": 0.4149459898471832, "max": 1.4618172645568848, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12643.3515625, "min": 12355.431640625, "max": 44345.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40510398149490356, "min": -0.10476311296224594, "max": 0.43668830394744873, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.16276550292969, "min": -25.143146514892578, "max": 116.59577941894531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01292134914547205, "min": 0.007899358868598938, "max": 0.2508623003959656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.450000286102295, "min": 2.030135154724121, "max": 60.20695495605469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06986299122218043, "min": 0.0648454232765029, "max": 0.07450793748752015, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.978081877110526, "min": 0.5055740482773332, "max": 1.0500078292194908, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013377986960265497, "min": 0.00012043791461638646, "max": 0.013417518230672621, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18729181744371695, "min": 0.0014452549753966376, "max": 0.1878452552294167, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.753961701092856e-06, "min": 7.753961701092856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010855546381529999, "min": 0.00010855546381529999, "max": 0.0032253478248840993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258462142857143, "min": 0.10258462142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361847, "min": 1.3691136000000002, "max": 2.3176183999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002682036807142857, "min": 0.0002682036807142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037548515299999996, "min": 0.0037548515299999996, "max": 0.10752407841, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011600017547607422, "min": 0.011399288661777973, "max": 0.39281731843948364, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1624002456665039, "min": 0.15959003567695618, "max": 2.7497212886810303, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 453.95384615384614, "min": 435.27941176470586, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29507.0, "min": 15984.0, "max": 32753.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3233030996052548, "min": -1.0000000521540642, "max": 1.477203150826787, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.69139837473631, "min": -32.000001668930054, "max": 96.39759847521782, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3233030996052548, "min": -1.0000000521540642, "max": 1.477203150826787, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.69139837473631, "min": -32.000001668930054, "max": 96.39759847521782, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05518667281330636, "min": 0.05222232431327621, "max": 7.411740625277162, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.531947060051607, "min": 3.2900064317364013, "max": 118.58785000443459, "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": "1698560317", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698562522" }, "total": 2205.5481747780004, "count": 1, "self": 0.8391638840002997, "children": { "run_training.setup": { "total": 0.0420756660000734, "count": 1, "self": 0.0420756660000734 }, "TrainerController.start_learning": { "total": 2204.666935228, "count": 1, "self": 1.5258462659749057, "children": { "TrainerController._reset_env": { "total": 3.5338060110000242, "count": 1, "self": 3.5338060110000242 }, "TrainerController.advance": { "total": 2199.482544122025, "count": 63450, "self": 1.5864850140751514, "children": { "env_step": { "total": 1569.2506224899676, "count": 63450, "self": 1426.2316820489827, "children": { "SubprocessEnvManager._take_step": { "total": 142.06768462393643, "count": 63450, "self": 4.829183049854919, "children": { "TorchPolicy.evaluate": { "total": 137.2385015740815, "count": 62555, "self": 137.2385015740815 } } }, "workers": { "total": 0.9512558170483771, "count": 63450, "self": 0.0, "children": { "worker_root": { "total": 2199.801969698969, "count": 63450, "is_parallel": true, "self": 896.901941788934, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020000139998046507, "count": 1, "is_parallel": true, "self": 0.0006833049997112539, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013167090000933968, "count": 8, "is_parallel": true, "self": 0.0013167090000933968 } } }, "UnityEnvironment.step": { "total": 0.0802530690000367, "count": 1, "is_parallel": true, "self": 0.0006221530002221698, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004965759999322472, "count": 1, "is_parallel": true, "self": 0.0004965759999322472 }, "communicator.exchange": { "total": 0.07743072399989614, "count": 1, "is_parallel": true, "self": 0.07743072399989614 }, "steps_from_proto": { "total": 0.001703615999986141, "count": 1, "is_parallel": true, "self": 0.00036749699984284234, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013361190001432988, "count": 8, "is_parallel": true, "self": 0.0013361190001432988 } } } } } } }, "UnityEnvironment.step": { "total": 1302.900027910035, "count": 63449, "is_parallel": true, "self": 36.105914641911795, "children": { "UnityEnvironment._generate_step_input": { "total": 26.79160279203188, "count": 63449, "is_parallel": true, "self": 26.79160279203188 }, "communicator.exchange": { "total": 1132.4091527530438, "count": 63449, "is_parallel": true, "self": 1132.4091527530438 }, "steps_from_proto": { "total": 107.59335772304757, "count": 63449, "is_parallel": true, "self": 22.413546863942656, "children": { "_process_rank_one_or_two_observation": { "total": 85.17981085910492, "count": 507592, "is_parallel": true, "self": 85.17981085910492 } } } } } } } } } } }, "trainer_advance": { "total": 628.6454366179823, "count": 63450, "self": 2.7926854970062323, "children": { "process_trajectory": { "total": 124.36549070897581, "count": 63450, "self": 124.09871779397554, "children": { "RLTrainer._checkpoint": { "total": 0.2667729150002742, "count": 2, "self": 0.2667729150002742 } } }, "_update_policy": { "total": 501.4872604120003, "count": 435, "self": 294.04544809299887, "children": { "TorchPPOOptimizer.update": { "total": 207.44181231900143, "count": 22788, "self": 207.44181231900143 } } } } } } }, "trainer_threads": { "total": 1.5360001270892099e-06, "count": 1, "self": 1.5360001270892099e-06 }, "TrainerController._save_models": { "total": 0.12473729299972547, "count": 1, "self": 0.00206398599948443, "children": { "RLTrainer._checkpoint": { "total": 0.12267330700024104, "count": 1, "self": 0.12267330700024104 } } } } } } }