{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48701709508895874, "min": 0.48701709508895874, "max": 1.453234314918518, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14711.8125, "min": 14711.8125, "max": 44085.31640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.366766095161438, "min": -0.11770842224359512, "max": 0.38068094849586487, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 97.92654418945312, "min": -28.36772918701172, "max": 102.02249145507812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005020562093704939, "min": -0.005020562093704939, "max": 0.3844617009162903, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3404901027679443, "min": -1.3404901027679443, "max": 91.11742401123047, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06650429094488751, "min": 0.06452916646717835, "max": 0.074182201540595, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9310600732284251, "min": 0.5069758057160754, "max": 1.0726229045249058, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012123220983449357, "min": 0.0010349651124159232, "max": 0.012123220983449357, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.169725093768291, "min": 0.012700949051325357, "max": 0.169725093768291, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4906689317142844e-06, "min": 7.4906689317142844e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010486936504399998, "min": 0.00010486936504399998, "max": 0.0035082995305668998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249685714285715, "min": 0.10249685714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349560000000001, "min": 1.3886848, "max": 2.569433100000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025943602857142863, "min": 0.00025943602857142863, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036321044000000007, "min": 0.0036321044000000007, "max": 0.11696636669, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013378906063735485, "min": 0.013378906063735485, "max": 0.45453396439552307, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18730469048023224, "min": 0.18730469048023224, "max": 3.1817376613616943, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 464.8939393939394, "min": 464.8939393939394, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30683.0, "min": 15984.0, "max": 32488.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3480307498803505, "min": -1.0000000521540642, "max": 1.404454820579098, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.62199874222279, "min": -29.15900156646967, "max": 87.62199874222279, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3480307498803505, "min": -1.0000000521540642, "max": 1.404454820579098, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.62199874222279, "min": -29.15900156646967, "max": 87.62199874222279, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06540422387053975, "min": 0.06540422387053975, "max": 9.845835037529469, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.251274551585084, "min": 4.195306989829987, "max": 157.5333606004715, "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": "1673797933", "python_version": "3.8.13 (default, Mar 28 2022, 11:38:47) \n[GCC 7.5.0]", "command_line_arguments": "/data1/zhenhuan_liu/anaconda3/envs/RL/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": "1.13.1+cu117", "numpy_version": "1.23.0", "end_time_seconds": "1673800185" }, "total": 2252.3173484392464, "count": 1, "self": 0.4731895215809345, "children": { "run_training.setup": { "total": 0.023103974759578705, "count": 1, "self": 0.023103974759578705 }, "TrainerController.start_learning": { "total": 2251.821054942906, "count": 1, "self": 1.0688426792621613, "children": { "TrainerController._reset_env": { "total": 2.6025934256613255, "count": 1, "self": 2.6025934256613255 }, "TrainerController.advance": { "total": 2248.0652400404215, "count": 63484, "self": 1.0037375800311565, "children": { "env_step": { "total": 1517.8782818131149, "count": 63484, "self": 1427.646456670016, "children": { "SubprocessEnvManager._take_step": { "total": 89.595104791224, "count": 63484, "self": 3.4567389339208603, "children": { "TorchPolicy.evaluate": { "total": 86.13836585730314, "count": 62558, "self": 31.229676488786936, "children": { "TorchPolicy.sample_actions": { "total": 54.90868936851621, "count": 62558, "self": 54.90868936851621 } } } } }, "workers": { "total": 0.6367203518748283, "count": 63484, "self": 0.0, "children": { "worker_root": { "total": 2248.1489797122777, "count": 63484, "is_parallel": true, "self": 932.9236842058599, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004011116921901703, "count": 1, "is_parallel": true, "self": 0.0012318603694438934, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027792565524578094, "count": 8, "is_parallel": true, "self": 0.0027792565524578094 } } }, "UnityEnvironment.step": { "total": 0.0603233203291893, "count": 1, "is_parallel": true, "self": 0.0008928850293159485, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008640959858894348, "count": 1, "is_parallel": true, "self": 0.0008640959858894348 }, "communicator.exchange": { "total": 0.05596811696887016, "count": 1, "is_parallel": true, "self": 0.05596811696887016 }, "steps_from_proto": { "total": 0.0025982223451137543, "count": 1, "is_parallel": true, "self": 0.0007000342011451721, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018981881439685822, "count": 8, "is_parallel": true, "self": 0.0018981881439685822 } } } } } } }, "UnityEnvironment.step": { "total": 1315.2252955064178, "count": 63483, "is_parallel": true, "self": 46.64189653471112, "children": { "UnityEnvironment._generate_step_input": { "total": 31.80939869210124, "count": 63483, "is_parallel": true, "self": 31.80939869210124 }, "communicator.exchange": { "total": 1109.8157677724957, "count": 63483, "is_parallel": true, "self": 1109.8157677724957 }, "steps_from_proto": { "total": 126.95823250710964, "count": 63483, "is_parallel": true, "self": 30.504945125430822, "children": { "_process_rank_one_or_two_observation": { "total": 96.45328738167882, "count": 507864, "is_parallel": true, "self": 96.45328738167882 } } } } } } } } } } }, "trainer_advance": { "total": 729.1832206472754, "count": 63484, "self": 2.089180864393711, "children": { "process_trajectory": { "total": 129.56884226948023, "count": 63484, "self": 129.37621860951185, "children": { "RLTrainer._checkpoint": { "total": 0.19262365996837616, "count": 2, "self": 0.19262365996837616 } } }, "_update_policy": { "total": 597.5251975134015, "count": 450, "self": 143.86967980861664, "children": { "TorchPPOOptimizer.update": { "total": 453.65551770478487, "count": 22812, "self": 453.65551770478487 } } } } } } }, "trainer_threads": { "total": 1.3224780559539795e-06, "count": 1, "self": 1.3224780559539795e-06 }, "TrainerController._save_models": { "total": 0.0843774750828743, "count": 1, "self": 0.0015897974371910095, "children": { "RLTrainer._checkpoint": { "total": 0.08278767764568329, "count": 1, "self": 0.08278767764568329 } } } } } } }