{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16493505239486694, "min": 0.15722300112247467, "max": 1.4052656888961792, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4924.30078125, "min": 4694.0498046875, "max": 42630.140625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999940.0, "min": 29952.0, "max": 2999940.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999940.0, "min": 29952.0, "max": 2999940.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8540011048316956, "min": -0.09912434220314026, "max": 0.9403629899024963, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 262.1783447265625, "min": -23.888965606689453, "max": 288.6914367675781, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009623406454920769, "min": -0.03946433588862419, "max": 0.5297891497612, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.954385757446289, "min": -11.720908164978027, "max": 125.56002807617188, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06870266597873954, "min": 0.06357189658325699, "max": 0.07392819888038848, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9618373237023535, "min": 0.49797110053012816, "max": 1.080816012102992, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015617611343305197, "min": 0.0002637795755519076, "max": 0.019331051370196896, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21864655880627276, "min": 0.0032141641293996184, "max": 0.24804761596412087, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.502413784942856e-06, "min": 1.502413784942856e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1033792989199984e-05, "min": 2.1033792989199984e-05, "max": 0.0038004319331894, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050077142857143, "min": 0.10050077142857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070108000000001, "min": 1.3962282666666668, "max": 2.7524886000000004, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0027065714285684e-05, "min": 6.0027065714285684e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008403789199999996, "min": 0.0008403789199999996, "max": 0.12669437894, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008398926816880703, "min": 0.00827715452760458, "max": 0.5762787461280823, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11758497357368469, "min": 0.11588016152381897, "max": 4.033951282501221, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 205.64827586206897, "min": 191.7814569536424, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29819.0, "min": 15984.0, "max": 34582.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7943517111498735, "min": -1.0000000521540642, "max": 1.807723673844808, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 260.18099811673164, "min": -31.99440163373947, "max": 281.78099808096886, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7943517111498735, "min": -1.0000000521540642, "max": 1.807723673844808, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 260.18099811673164, "min": -31.99440163373947, "max": 281.78099808096886, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017978564487942817, "min": 0.016890301481762435, "max": 12.210996367037296, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6068918507517083, "min": 2.5087846337846713, "max": 195.37594187259674, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710699308", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710711197" }, "total": 11889.228364234, "count": 1, "self": 1.0535574390014517, "children": { "run_training.setup": { "total": 0.07496412099999361, "count": 1, "self": 0.07496412099999361 }, "TrainerController.start_learning": { "total": 11888.099842673999, "count": 1, "self": 7.377497912835679, "children": { "TrainerController._reset_env": { "total": 3.9106495799999266, "count": 1, "self": 3.9106495799999266 }, "TrainerController.advance": { "total": 11876.692539916163, "count": 195724, "self": 8.824618831171392, "children": { "env_step": { "total": 8353.853176937842, "count": 195724, "self": 7803.285286021739, "children": { "SubprocessEnvManager._take_step": { "total": 545.6716710541439, "count": 195724, "self": 23.433468841969216, "children": { "TorchPolicy.evaluate": { "total": 522.2382022121747, "count": 187543, "self": 522.2382022121747 } } }, "workers": { "total": 4.8962198619597075, "count": 195724, "self": 0.0, "children": { "worker_root": { "total": 11865.206947440842, "count": 195724, "is_parallel": true, "self": 4689.132233899832, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008392254000000321, "count": 1, "is_parallel": true, "self": 0.005655421000028582, "children": { "_process_rank_one_or_two_observation": { "total": 0.002736832999971739, "count": 8, "is_parallel": true, "self": 0.002736832999971739 } } }, "UnityEnvironment.step": { "total": 0.07443668899986733, "count": 1, "is_parallel": true, "self": 0.0009194399999614689, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004565690001072653, "count": 1, "is_parallel": true, "self": 0.0004565690001072653 }, "communicator.exchange": { "total": 0.07076491999987411, "count": 1, "is_parallel": true, "self": 0.07076491999987411 }, "steps_from_proto": { "total": 0.002295759999924485, "count": 1, "is_parallel": true, "self": 0.0005367839999053103, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017589760000191745, "count": 8, "is_parallel": true, "self": 0.0017589760000191745 } } } } } } }, "UnityEnvironment.step": { "total": 7176.07471354101, "count": 195723, "is_parallel": true, "self": 165.42886984504275, "children": { "UnityEnvironment._generate_step_input": { "total": 90.09803844408157, "count": 195723, "is_parallel": true, "self": 90.09803844408157 }, "communicator.exchange": { "total": 6498.039740155298, "count": 195723, "is_parallel": true, "self": 6498.039740155298 }, "steps_from_proto": { "total": 422.5080650965874, "count": 195723, "is_parallel": true, "self": 92.30878885402171, "children": { "_process_rank_one_or_two_observation": { "total": 330.1992762425657, "count": 1565784, "is_parallel": true, "self": 330.1992762425657 } } } } } } } } } } }, "trainer_advance": { "total": 3514.014744147148, "count": 195724, "self": 16.7373286035845, "children": { "process_trajectory": { "total": 561.7438691225746, "count": 195724, "self": 560.910314013576, "children": { "RLTrainer._checkpoint": { "total": 0.8335551089985529, "count": 6, "self": 0.8335551089985529 } } }, "_update_policy": { "total": 2935.5335464209893, "count": 1393, "self": 1152.1382941152435, "children": { "TorchPPOOptimizer.update": { "total": 1783.3952523057458, "count": 68436, "self": 1783.3952523057458 } } } } } } }, "trainer_threads": { "total": 1.1129995982628316e-06, "count": 1, "self": 1.1129995982628316e-06 }, "TrainerController._save_models": { "total": 0.11915415200019197, "count": 1, "self": 0.0038178369995875983, "children": { "RLTrainer._checkpoint": { "total": 0.11533631500060437, "count": 1, "self": 0.11533631500060437 } } } } } } }