{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5354316830635071, "min": 0.5354316830635071, "max": 1.4879765510559082, "count": 24 }, "Pyramids.Policy.Entropy.sum": { "value": 16071.517578125, "min": 16071.517578125, "max": 45139.2578125, "count": 24 }, "Pyramids.Step.mean": { "value": 719967.0, "min": 29965.0, "max": 719967.0, "count": 24 }, "Pyramids.Step.sum": { "value": 719967.0, "min": 29965.0, "max": 719967.0, "count": 24 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46009257435798645, "min": -0.1223444864153862, "max": 0.46009257435798645, "count": 24 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.2249984741211, "min": -29.11798858642578, "max": 124.2249984741211, "count": 24 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021058104932308197, "min": -0.012443069368600845, "max": 0.4489564597606659, "count": 24 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.685688495635986, "min": -3.2351980209350586, "max": 106.85163879394531, "count": 24 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07148070406540119, "min": 0.06517403315713939, "max": 0.07585844562453523, "count": 24 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0007298569156167, "min": 0.5154042914586715, "max": 1.0817758405270674, "count": 24 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01528131502328463, "min": 0.0007489936297205103, "max": 0.01528131502328463, "count": 24 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21393841032598482, "min": 0.008987923556646123, "max": 0.21393841032598482, "count": 24 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00022950117349961665, "min": 0.00022950117349961665, "max": 0.0002984126148148429, "count": 24 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.003213016428994633, "min": 0.0020888883037039003, "max": 0.0038853469048843988, "count": 24 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.17650038333333332, "min": 0.17650038333333332, "max": 0.19947087142857142, "count": 24 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.4710053666666663, "min": 1.3962961, "max": 2.7674782000000007, "count": 24 }, "Pyramids.Policy.Beta.mean": { "value": 0.007652388295, "min": 0.007652388295, "max": 0.009947140055714286, "count": 24 }, "Pyramids.Policy.Beta.sum": { "value": 0.10713343613, "min": 0.06962998039, "max": 0.12952204843999998, "count": 24 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010132000781595707, "min": 0.010132000781595707, "max": 0.31084755063056946, "count": 24 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14184801280498505, "min": 0.14184801280498505, "max": 2.1759328842163086, "count": 24 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 421.72, "min": 421.72, "max": 999.0, "count": 24 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31629.0, "min": 16636.0, "max": 32708.0, "count": 24 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5249386477470397, "min": -0.999987552408129, "max": 1.5249386477470397, "count": 24 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.37039858102798, "min": -31.999601677060127, "max": 114.37039858102798, "count": 24 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5249386477470397, "min": -0.999987552408129, "max": 1.5249386477470397, "count": 24 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.37039858102798, "min": -31.999601677060127, "max": 114.37039858102798, "count": 24 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04477264853582407, "min": 0.04477264853582407, "max": 5.834203359177884, "count": 24 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3579486401868053, "min": 3.200345461082179, "max": 99.18145710602403, "count": 24 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 24 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 24 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690474902", "python_version": "3.8.16 (default, Jun 12 2023, 18:09:05) \n[GCC 11.2.0]", "command_line_arguments": "/global/home/users/lizhen/scratch/miniconda3/envs/huggingface/bin/mlagents-learn ../ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690476910" }, "total": 2007.4402644950023, "count": 1, "self": 0.019585551985073835, "children": { "run_training.setup": { "total": 0.0628495890123304, "count": 1, "self": 0.0628495890123304 }, "TrainerController.start_learning": { "total": 2007.357829354005, "count": 1, "self": 0.9330457296455279, "children": { "TrainerController._reset_env": { "total": 17.90129806101322, "count": 1, "self": 17.90129806101322 }, "TrainerController.advance": { "total": 1986.292932489363, "count": 47287, "self": 0.8639501665020362, "children": { "env_step": { "total": 1415.4523650843475, "count": 47287, "self": 1341.8168204505346, "children": { "SubprocessEnvManager._take_step": { "total": 73.07705894342507, "count": 47287, "self": 3.1242650105268694, "children": { "TorchPolicy.evaluate": { "total": 69.9527939328982, "count": 46550, "self": 69.9527939328982 } } }, "workers": { "total": 0.5584856903878972, "count": 47286, "self": 0.0, "children": { "worker_root": { "total": 2001.7802101577108, "count": 47286, "is_parallel": true, "self": 753.0852439897717, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.013564358989242464, "count": 1, "is_parallel": true, "self": 0.002854533988283947, "children": { "_process_rank_one_or_two_observation": { "total": 0.010709825000958517, "count": 8, "is_parallel": true, "self": 0.010709825000958517 } } }, "UnityEnvironment.step": { "total": 0.06518930001766421, "count": 1, "is_parallel": true, "self": 0.0010782770114019513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008892060141079128, "count": 1, "is_parallel": true, "self": 0.0008892060141079128 }, "communicator.exchange": { "total": 0.05995043198345229, "count": 1, "is_parallel": true, "self": 0.05995043198345229 }, "steps_from_proto": { "total": 0.0032713850087020546, "count": 1, "is_parallel": true, "self": 0.0007223400461953133, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025490449625067413, "count": 8, "is_parallel": true, "self": 0.0025490449625067413 } } } } } } }, "UnityEnvironment.step": { "total": 1248.6949661679391, "count": 47285, "is_parallel": true, "self": 44.633973296004115, "children": { "UnityEnvironment._generate_step_input": { "total": 33.083338855649345, "count": 47285, "is_parallel": true, "self": 33.083338855649345 }, "communicator.exchange": { "total": 1047.8523495950503, "count": 47285, "is_parallel": true, "self": 1047.8523495950503 }, "steps_from_proto": { "total": 123.12530442123534, "count": 47285, "is_parallel": true, "self": 26.948400199238677, "children": { "_process_rank_one_or_two_observation": { "total": 96.17690422199667, "count": 378280, "is_parallel": true, "self": 96.17690422199667 } } } } } } } } } } }, "trainer_advance": { "total": 569.9766172385134, "count": 47286, "self": 1.657787573582027, "children": { "process_trajectory": { "total": 71.81227012249292, "count": 47286, "self": 71.64519006150658, "children": { "RLTrainer._checkpoint": { "total": 0.16708006098633632, "count": 1, "self": 0.16708006098633632 } } }, "_update_policy": { "total": 496.5065595424385, "count": 330, "self": 251.4980613142252, "children": { "TorchPPOOptimizer.update": { "total": 245.00849822821328, "count": 16938, "self": 245.00849822821328 } } } } } } }, "trainer_threads": { "total": 3.762979758903384e-06, "count": 1, "self": 3.762979758903384e-06 }, "TrainerController._save_models": { "total": 2.230549311003415, "count": 1, "self": 0.017922976025147364, "children": { "RLTrainer._checkpoint": { "total": 2.2126263349782676, "count": 1, "self": 2.2126263349782676 } } } } } } }