{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3167525827884674, "min": 0.3167525827884674, "max": 1.3282514810562134, "count": 45 }, "Pyramids.Policy.Entropy.sum": { "value": 9497.509765625, "min": 9497.509765625, "max": 40293.8359375, "count": 45 }, "Pyramids.Step.mean": { "value": 1349934.0, "min": 29999.0, "max": 1349934.0, "count": 45 }, "Pyramids.Step.sum": { "value": 1349934.0, "min": 29999.0, "max": 1349934.0, "count": 45 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7149131298065186, "min": -0.09940466284751892, "max": 0.7285493612289429, "count": 45 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 205.8949737548828, "min": -23.956523895263672, "max": 210.944091796875, "count": 45 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013993170112371445, "min": -0.03173583000898361, "max": 0.5168747305870056, "count": 45 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.030033111572266, "min": -8.981240272521973, "max": 123.01618957519531, "count": 45 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0679142276279717, "min": 0.06605978302244615, "max": 0.07343552512609666, "count": 45 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9507991867916038, "min": 0.5080930966838403, "max": 1.0550689952603232, "count": 45 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014197500764220465, "min": 0.0005210101510204605, "max": 0.01764622042052603, "count": 45 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1987650106990865, "min": 0.0072941421142864475, "max": 0.24704708588736443, "count": 45 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00016654085877210956, "min": 0.00016654085877210956, "max": 0.00029841212910071906, "count": 45 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002331572022809534, "min": 0.0020888849037050336, "max": 0.0040527834490722, "count": 45 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1555136047619048, "min": 0.1555136047619048, "max": 0.19947070952380955, "count": 45 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.177190466666667, "min": 1.3962949666666669, "max": 2.7523924666666666, "count": 45 }, "Pyramids.Policy.Beta.mean": { "value": 0.0055558091157142855, "min": 0.0055558091157142855, "max": 0.009947123881428571, "count": 45 }, "Pyramids.Policy.Beta.sum": { "value": 0.07778132762, "min": 0.06962986717, "max": 0.13509768722, "count": 45 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008170568384230137, "min": 0.006660111714154482, "max": 0.4152999520301819, "count": 45 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11438795924186707, "min": 0.09324156492948532, "max": 2.907099723815918, "count": 45 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 274.5, "min": 254.94017094017093, "max": 998.75, "count": 45 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30195.0, "min": 16670.0, "max": 33168.0, "count": 45 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.690837823055886, "min": -0.9370188026223332, "max": 1.743905157364648, "count": 45 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 187.68299835920334, "min": -29.98460168391466, "max": 202.29299825429916, "count": 45 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.690837823055886, "min": -0.9370188026223332, "max": 1.743905157364648, "count": 45 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 187.68299835920334, "min": -29.98460168391466, "max": 202.29299825429916, "count": 45 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02314725231770206, "min": 0.01985042568163148, "max": 7.671826935866299, "count": 45 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5693450072649284, "min": 2.0758601336710854, "max": 130.4210579097271, "count": 45 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 45 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 45 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708452728", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708455722" }, "total": 2994.21582929, "count": 1, "self": 0.5800379889997203, "children": { "run_training.setup": { "total": 0.0690948589999607, "count": 1, "self": 0.0690948589999607 }, "TrainerController.start_learning": { "total": 2993.566696442, "count": 1, "self": 1.9040499141351575, "children": { "TrainerController._reset_env": { "total": 2.817332537999846, "count": 1, "self": 2.817332537999846 }, "TrainerController.advance": { "total": 2988.8451917208654, "count": 87175, "self": 1.9733178476390094, "children": { "env_step": { "total": 2145.1048334829934, "count": 87175, "self": 1962.0632417189154, "children": { "SubprocessEnvManager._take_step": { "total": 181.86222587105794, "count": 87175, "self": 6.596621490120015, "children": { "TorchPolicy.evaluate": { "total": 175.26560438093793, "count": 84737, "self": 175.26560438093793 } } }, "workers": { "total": 1.1793658930200763, "count": 87174, "self": 0.0, "children": { "worker_root": { "total": 2986.769386699989, "count": 87174, "is_parallel": true, "self": 1187.7653881350388, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003026042999863421, "count": 1, "is_parallel": true, "self": 0.0008700200005478109, "children": { "_process_rank_one_or_two_observation": { "total": 0.00215602299931561, "count": 8, "is_parallel": true, "self": 0.00215602299931561 } } }, "UnityEnvironment.step": { "total": 0.04870142700019642, "count": 1, "is_parallel": true, "self": 0.000580281000566174, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005262729996502458, "count": 1, "is_parallel": true, "self": 0.0005262729996502458 }, "communicator.exchange": { "total": 0.045961736000208475, "count": 1, "is_parallel": true, "self": 0.045961736000208475 }, "steps_from_proto": { "total": 0.0016331369997715228, "count": 1, "is_parallel": true, "self": 0.00037260799945215695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012605290003193659, "count": 8, "is_parallel": true, "self": 0.0012605290003193659 } } } } } } }, "UnityEnvironment.step": { "total": 1799.00399856495, "count": 87173, "is_parallel": true, "self": 47.62089760097251, "children": { "UnityEnvironment._generate_step_input": { "total": 35.165474063924194, "count": 87173, "is_parallel": true, "self": 35.165474063924194 }, "communicator.exchange": { "total": 1576.1375383689979, "count": 87173, "is_parallel": true, "self": 1576.1375383689979 }, "steps_from_proto": { "total": 140.08008853105548, "count": 87173, "is_parallel": true, "self": 28.773405101110257, "children": { "_process_rank_one_or_two_observation": { "total": 111.30668342994522, "count": 697384, "is_parallel": true, "self": 111.30668342994522 } } } } } } } } } } }, "trainer_advance": { "total": 841.767040390233, "count": 87174, "self": 3.7603928002386056, "children": { "process_trajectory": { "total": 175.2177874980107, "count": 87174, "self": 174.9652226670105, "children": { "RLTrainer._checkpoint": { "total": 0.2525648310001998, "count": 2, "self": 0.2525648310001998 } } }, "_update_policy": { "total": 662.7888600919837, "count": 623, "self": 386.84931964294356, "children": { "TorchPPOOptimizer.update": { "total": 275.9395404490401, "count": 30858, "self": 275.9395404490401 } } } } } } }, "trainer_threads": { "total": 1.3859998944099061e-06, "count": 1, "self": 1.3859998944099061e-06 }, "TrainerController._save_models": { "total": 0.0001208829999086447, "count": 1, "self": 2.2500000341096893e-05, "children": { "RLTrainer._checkpoint": { "total": 9.838299956754781e-05, "count": 1, "self": 9.838299956754781e-05 } } } } } } }