{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3336308002471924, "min": 0.3336308002471924, "max": 1.4739867448806763, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9928.8525390625, "min": 9928.8525390625, "max": 44714.86328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6524842977523804, "min": -0.1032743901014328, "max": 0.7222211360931396, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.95802307128906, "min": -24.992403030395508, "max": 207.2774658203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014233765192329884, "min": -0.014584774151444435, "max": 0.5624263286590576, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.0566229820251465, "min": -4.054567337036133, "max": 133.2950439453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06715620267839191, "min": 0.06391471691916471, "max": 0.07474561396761079, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9401868374974868, "min": 0.47236056482113614, "max": 1.0600206978814837, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015102194202599162, "min": 0.00021988153755070396, "max": 0.018140168579976326, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21143071883638828, "min": 0.0026385784506084476, "max": 0.22722500430616346, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.562433193507139e-06, "min": 7.562433193507139e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010587406470909995, "min": 0.00010587406470909995, "max": 0.0036317920894026992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252077857142858, "min": 0.10252077857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352909, "min": 1.3691136000000002, "max": 2.6105973, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026182577928571423, "min": 0.00026182577928571423, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003665560909999999, "min": 0.003665560909999999, "max": 0.12107867027000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013648114167153835, "min": 0.013648114167153835, "max": 0.729371190071106, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19107359647750854, "min": 0.19107359647750854, "max": 5.105598449707031, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 305.66336633663366, "min": 261.74766355140184, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30872.0, "min": 15984.0, "max": 33145.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6568646872160482, "min": -1.0000000521540642, "max": 1.738252324060859, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 169.0001980960369, "min": -32.000001668930054, "max": 187.07699754834175, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6568646872160482, "min": -1.0000000521540642, "max": 1.738252324060859, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 169.0001980960369, "min": -32.000001668930054, "max": 187.07699754834175, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042576474308803236, "min": 0.03839342447463423, "max": 15.976162689737976, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.34280037949793, "min": 4.108096418785863, "max": 255.6186030358076, "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": "1673803442", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:06) \n[GCC 11.3.0]", "command_line_arguments": "/home/emmanuel/Documents/code/rl/ml-agents/venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.20.0", "end_time_seconds": "1673805435" }, "total": 1992.2478150590032, "count": 1, "self": 0.3718441579840146, "children": { "run_training.setup": { "total": 0.25807200200506486, "count": 1, "self": 0.25807200200506486 }, "TrainerController.start_learning": { "total": 1991.617898899014, "count": 1, "self": 1.5770891454594675, "children": { "TrainerController._reset_env": { "total": 1.995607110002311, "count": 1, "self": 1.995607110002311 }, "TrainerController.advance": { "total": 1987.8867047335661, "count": 64181, "self": 1.5895608359423932, "children": { "env_step": { "total": 1147.5368528595136, "count": 64181, "self": 1056.775928500254, "children": { "SubprocessEnvManager._take_step": { "total": 89.77668651469867, "count": 64181, "self": 4.4662404021655675, "children": { "TorchPolicy.evaluate": { "total": 85.3104461125331, "count": 62557, "self": 19.557115692587104, "children": { "TorchPolicy.sample_actions": { "total": 65.753330419946, "count": 62557, "self": 65.753330419946 } } } } }, "workers": { "total": 0.9842378445609938, "count": 64181, "self": 0.0, "children": { "worker_root": { "total": 1988.2228884786018, "count": 64181, "is_parallel": true, "self": 1036.3317487975874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002067510999040678, "count": 1, "is_parallel": true, "self": 0.0006967409863136709, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013707700127270073, "count": 8, "is_parallel": true, "self": 0.0013707700127270073 } } }, "UnityEnvironment.step": { "total": 0.10326555199571885, "count": 1, "is_parallel": true, "self": 0.0003784889995586127, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008382520172744989, "count": 1, "is_parallel": true, "self": 0.0008382520172744989 }, "communicator.exchange": { "total": 0.10093908198177814, "count": 1, "is_parallel": true, "self": 0.10093908198177814 }, "steps_from_proto": { "total": 0.0011097289971075952, "count": 1, "is_parallel": true, "self": 0.0002831730234902352, "children": { "_process_rank_one_or_two_observation": { "total": 0.00082655597361736, "count": 8, "is_parallel": true, "self": 0.00082655597361736 } } } } } } }, "UnityEnvironment.step": { "total": 951.8911396810145, "count": 64180, "is_parallel": true, "self": 22.411985482642194, "children": { "UnityEnvironment._generate_step_input": { "total": 16.6701868257951, "count": 64180, "is_parallel": true, "self": 16.6701868257951 }, "communicator.exchange": { "total": 844.2288554826519, "count": 64180, "is_parallel": true, "self": 844.2288554826519 }, "steps_from_proto": { "total": 68.58011188992532, "count": 64180, "is_parallel": true, "self": 17.461721953790402, "children": { "_process_rank_one_or_two_observation": { "total": 51.11838993613492, "count": 513440, "is_parallel": true, "self": 51.11838993613492 } } } } } } } } } } }, "trainer_advance": { "total": 838.7602910381102, "count": 64181, "self": 2.867345807579113, "children": { "process_trajectory": { "total": 148.39430403569713, "count": 64181, "self": 147.1580371716991, "children": { "RLTrainer._checkpoint": { "total": 1.2362668639980257, "count": 2, "self": 1.2362668639980257 } } }, "_update_policy": { "total": 687.4986411948339, "count": 450, "self": 217.11618643419934, "children": { "TorchPPOOptimizer.update": { "total": 470.3824547606346, "count": 22791, "self": 470.3824547606346 } } } } } } }, "trainer_threads": { "total": 1.000997144728899e-06, "count": 1, "self": 1.000997144728899e-06 }, "TrainerController._save_models": { "total": 0.15849690898903646, "count": 1, "self": 0.0015820829721633345, "children": { "RLTrainer._checkpoint": { "total": 0.15691482601687312, "count": 1, "self": 0.15691482601687312 } } } } } } }