{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5566681623458862, "min": 0.5566681623458862, "max": 1.411436915397644, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16610.978515625, "min": 16610.978515625, "max": 42817.3515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.10048738867044449, "min": -0.09501564502716064, "max": 0.10048738867044449, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 25.32282257080078, "min": -22.993785858154297, "max": 25.32282257080078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.0951638221740723, "min": -1.0951638221740723, "max": 0.7270631194114685, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -275.9812927246094, "min": -275.9812927246094, "max": 172.31396484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06819585493744738, "min": 0.06468939948454466, "max": 0.0719580957919324, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9547419691242633, "min": 0.4985635484332599, "max": 1.0355263534293044, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.5350938461630779, "min": 0.000572242107563186, "max": 0.5350938461630779, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 7.491313846283091, "min": 0.008011389505884604, "max": 7.491313846283091, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.652818877664283e-06, "min": 7.652818877664283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010713946428729995, "min": 0.00010713946428729995, "max": 0.0035082242305919994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255090714285715, "min": 0.10255090714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357127, "min": 1.3691136000000002, "max": 2.5694080000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002648356235714285, "min": 0.0002648356235714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003707698729999999, "min": 0.003707698729999999, "max": 0.1169638592, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02236977592110634, "min": 0.021324397996068, "max": 0.8654512166976929, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.31317687034606934, "min": 0.2985415756702423, "max": 6.0581583976745605, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 785.1282051282051, "min": 736.0243902439024, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30620.0, "min": 15984.0, "max": 32509.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.44547688044034517, "min": -1.0000000521540642, "max": 0.6784243487366816, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 17.373598337173462, "min": -32.000001668930054, "max": 27.815398298203945, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.44547688044034517, "min": -1.0000000521540642, "max": 0.6784243487366816, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 17.373598337173462, "min": -32.000001668930054, "max": 27.815398298203945, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.18498469028735343, "min": 0.17635261680272113, "max": 18.286585453897715, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 7.2144029212067835, "min": 6.2853307200130075, "max": 292.58536726236343, "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": "1768208856", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/why/miniconda3/envs/drl-310/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1768211056" }, "total": 2200.2616342832334, "count": 1, "self": 0.42367820674553514, "children": { "run_training.setup": { "total": 0.02777264639735222, "count": 1, "self": 0.02777264639735222 }, "TrainerController.start_learning": { "total": 2199.8101834300905, "count": 1, "self": 1.6601906581781805, "children": { "TrainerController._reset_env": { "total": 3.9391733771190047, "count": 1, "self": 3.9391733771190047 }, "TrainerController.advance": { "total": 2194.142838410102, "count": 63245, "self": 1.5322132161818445, "children": { "env_step": { "total": 1490.164380254224, "count": 63245, "self": 1323.56980460044, "children": { "SubprocessEnvManager._take_step": { "total": 165.61565620778129, "count": 63245, "self": 5.352107660379261, "children": { "TorchPolicy.evaluate": { "total": 160.26354854740202, "count": 62564, "self": 160.26354854740202 } } }, "workers": { "total": 0.978919446002692, "count": 63245, "self": 0.0, "children": { "worker_root": { "total": 2196.549942309037, "count": 63245, "is_parallel": true, "self": 994.6834193221293, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002227352000772953, "count": 1, "is_parallel": true, "self": 0.0006672232411801815, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015601287595927715, "count": 8, "is_parallel": true, "self": 0.0015601287595927715 } } }, "UnityEnvironment.step": { "total": 0.05159895867109299, "count": 1, "is_parallel": true, "self": 0.0003917650319635868, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041465088725090027, "count": 1, "is_parallel": true, "self": 0.00041465088725090027 }, "communicator.exchange": { "total": 0.04945392766967416, "count": 1, "is_parallel": true, "self": 0.04945392766967416 }, "steps_from_proto": { "total": 0.0013386150822043419, "count": 1, "is_parallel": true, "self": 0.00032070185989141464, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010179132223129272, "count": 8, "is_parallel": true, "self": 0.0010179132223129272 } } } } } } }, "UnityEnvironment.step": { "total": 1201.8665229869075, "count": 63244, "is_parallel": true, "self": 34.03102416265756, "children": { "UnityEnvironment._generate_step_input": { "total": 22.572350355796516, "count": 63244, "is_parallel": true, "self": 22.572350355796516 }, "communicator.exchange": { "total": 1051.9862810336053, "count": 63244, "is_parallel": true, "self": 1051.9862810336053 }, "steps_from_proto": { "total": 93.2768674348481, "count": 63244, "is_parallel": true, "self": 19.910870287567377, "children": { "_process_rank_one_or_two_observation": { "total": 73.36599714728072, "count": 505952, "is_parallel": true, "self": 73.36599714728072 } } } } } } } } } } }, "trainer_advance": { "total": 702.446244939696, "count": 63245, "self": 3.6186434887349606, "children": { "process_trajectory": { "total": 115.99579880386591, "count": 63245, "self": 115.82062784116715, "children": { "RLTrainer._checkpoint": { "total": 0.17517096269875765, "count": 2, "self": 0.17517096269875765 } } }, "_update_policy": { "total": 582.8318026470952, "count": 445, "self": 300.65978278266266, "children": { "TorchPPOOptimizer.update": { "total": 282.1720198644325, "count": 22803, "self": 282.1720198644325 } } } } } } }, "trainer_threads": { "total": 6.579793989658356e-07, "count": 1, "self": 6.579793989658356e-07 }, "TrainerController._save_models": { "total": 0.0679803267121315, "count": 1, "self": 0.001256277784705162, "children": { "RLTrainer._checkpoint": { "total": 0.06672404892742634, "count": 1, "self": 0.06672404892742634 } } } } } } }