{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6160495281219482, "min": 0.6093841195106506, "max": 1.3897463083267212, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18599.767578125, "min": 18408.275390625, "max": 42159.34375, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29996.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29996.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43479880690574646, "min": -0.12259074300527573, "max": 0.535243570804596, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 116.96087646484375, "min": -29.176597595214844, "max": 146.65673828125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06376861035823822, "min": -0.01667921617627144, "max": 0.36044588685035706, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 17.153757095336914, "min": -4.403313159942627, "max": 86.86746215820312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06726242829366433, "min": 0.06489429489726992, "max": 0.07389396612208136, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9416739961113005, "min": 0.5274496376786197, "max": 1.0647492395316174, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012002619287938745, "min": 0.0003404957719820241, "max": 0.015414567366471081, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16803667003114242, "min": 0.004065029767002356, "max": 0.21607641108372871, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4099475300499955e-06, "min": 7.4099475300499955e-06, "max": 0.00029484945171685004, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010373926542069994, "min": 0.00010373926542069994, "max": 0.0033826604724466, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246995000000002, "min": 0.10246995000000002, "max": 0.19828315000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345793000000002, "min": 1.4345793000000002, "max": 2.5275534000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002567480049999999, "min": 0.0002567480049999999, "max": 0.009828486684999999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035944720699999985, "min": 0.0035944720699999985, "max": 0.11278258466000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00805074255913496, "min": 0.00805074255913496, "max": 0.541143536567688, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11271040141582489, "min": 0.11271040141582489, "max": 4.329148292541504, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 424.6764705882353, "min": 360.8433734939759, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28878.0, "min": 16283.0, "max": 32752.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3693940985728712, "min": -0.9999375520274043, "max": 1.5668481766100388, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.11879870295525, "min": -31.998001664876938, "max": 130.04839865863323, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3693940985728712, "min": -0.9999375520274043, "max": 1.5668481766100388, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.11879870295525, "min": -31.998001664876938, "max": 130.04839865863323, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03584493006158428, "min": 0.0338602943366242, "max": 11.280355455244289, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4374552441877313, "min": 2.4374552441877313, "max": 191.7660427391529, "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": "1727024589", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727026822" }, "total": 2233.4375273699998, "count": 1, "self": 0.48962489599989567, "children": { "run_training.setup": { "total": 0.05216245900010108, "count": 1, "self": 0.05216245900010108 }, "TrainerController.start_learning": { "total": 2232.895740015, "count": 1, "self": 1.3713316260009378, "children": { "TrainerController._reset_env": { "total": 2.1563812039998993, "count": 1, "self": 2.1563812039998993 }, "TrainerController.advance": { "total": 2229.303511764999, "count": 63627, "self": 1.3527722009916943, "children": { "env_step": { "total": 1429.588737249014, "count": 63627, "self": 1324.996720927954, "children": { "SubprocessEnvManager._take_step": { "total": 103.76874994705668, "count": 63627, "self": 4.608621051025693, "children": { "TorchPolicy.evaluate": { "total": 99.16012889603098, "count": 62561, "self": 99.16012889603098 } } }, "workers": { "total": 0.8232663740034241, "count": 63627, "self": 0.0, "children": { "worker_root": { "total": 2227.981373906985, "count": 63627, "is_parallel": true, "self": 1021.0219533739696, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002621614999952726, "count": 1, "is_parallel": true, "self": 0.0007389169998077705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018826980001449556, "count": 8, "is_parallel": true, "self": 0.0018826980001449556 } } }, "UnityEnvironment.step": { "total": 0.1002839259999746, "count": 1, "is_parallel": true, "self": 0.0006602199998724245, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044013599995196273, "count": 1, "is_parallel": true, "self": 0.00044013599995196273 }, "communicator.exchange": { "total": 0.0923262840001371, "count": 1, "is_parallel": true, "self": 0.0923262840001371 }, "steps_from_proto": { "total": 0.006857286000013119, "count": 1, "is_parallel": true, "self": 0.00036737199980052537, "children": { "_process_rank_one_or_two_observation": { "total": 0.006489914000212593, "count": 8, "is_parallel": true, "self": 0.006489914000212593 } } } } } } }, "UnityEnvironment.step": { "total": 1206.9594205330154, "count": 63626, "is_parallel": true, "self": 33.06978756404874, "children": { "UnityEnvironment._generate_step_input": { "total": 22.50551274498116, "count": 63626, "is_parallel": true, "self": 22.50551274498116 }, "communicator.exchange": { "total": 1057.0431491099962, "count": 63626, "is_parallel": true, "self": 1057.0431491099962 }, "steps_from_proto": { "total": 94.34097111398933, "count": 63626, "is_parallel": true, "self": 18.976875728015784, "children": { "_process_rank_one_or_two_observation": { "total": 75.36409538597354, "count": 509008, "is_parallel": true, "self": 75.36409538597354 } } } } } } } } } } }, "trainer_advance": { "total": 798.3620023149931, "count": 63627, "self": 2.6710232680313766, "children": { "process_trajectory": { "total": 125.1857095709654, "count": 63627, "self": 125.00212068996575, "children": { "RLTrainer._checkpoint": { "total": 0.18358888099965043, "count": 2, "self": 0.18358888099965043 } } }, "_update_policy": { "total": 670.5052694759963, "count": 450, "self": 285.2489153439758, "children": { "TorchPPOOptimizer.update": { "total": 385.25635413202053, "count": 22785, "self": 385.25635413202053 } } } } } } }, "trainer_threads": { "total": 9.54999904934084e-07, "count": 1, "self": 9.54999904934084e-07 }, "TrainerController._save_models": { "total": 0.06451446500022939, "count": 1, "self": 0.001570430000356282, "children": { "RLTrainer._checkpoint": { "total": 0.06294403499987311, "count": 1, "self": 0.06294403499987311 } } } } } } }