{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8183311820030212, "min": 0.8055682182312012, "max": 1.4012336730957031, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 24484.46875, "min": 24463.49609375, "max": 42507.82421875, "count": 16 }, "Pyramids.Step.mean": { "value": 479990.0, "min": 29944.0, "max": 479990.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479990.0, "min": 29944.0, "max": 479990.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.15364865958690643, "min": -0.1094219759106636, "max": 0.15364865958690643, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 38.258514404296875, "min": -26.370697021484375, "max": 38.78314971923828, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008429978042840958, "min": -0.031803976744413376, "max": 0.4299536645412445, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.099064588546753, "min": -8.046405792236328, "max": 101.89901733398438, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0683730426782084, "min": 0.06554761269439274, "max": 0.07343078332616845, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9572225974949177, "min": 0.5095508464586308, "max": 1.1014617498925268, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009736797886205453, "min": 0.000390742249709338, "max": 0.011931707416402386, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13631517040687635, "min": 0.005470391495930732, "max": 0.17897561124603578, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.07459930847e-05, "min": 2.07459930847e-05, "max": 0.00029046651746354285, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002904439031858, "min": 0.0002904439031858, "max": 0.0033160147946618, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1069153, "min": 0.1069153, "max": 0.19682217142857145, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4968142, "min": 1.3777552000000002, "max": 2.4231127999999997, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007008384700000001, "min": 0.0007008384700000001, "max": 0.009682534925714286, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.009811738580000002, "min": 0.009811738580000002, "max": 0.11055328618, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01960540935397148, "min": 0.01960540935397148, "max": 0.47367724776268005, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.27447572350502014, "min": 0.27447572350502014, "max": 3.3157408237457275, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 691.625, "min": 668.4897959183673, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27665.0, "min": 16743.0, "max": 32756.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5581449603661894, "min": -0.9997677930420444, "max": 0.6599541304943463, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 22.32579841464758, "min": -30.99280158430338, "max": 31.67779826372862, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5581449603661894, "min": -0.9997677930420444, "max": 0.6599541304943463, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 22.32579841464758, "min": -30.99280158430338, "max": 31.67779826372862, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.14021317574515707, "min": 0.14021317574515707, "max": 9.079531007829834, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 5.608527029806282, "min": 5.608527029806282, "max": 154.35202713310719, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1670423197", "python_version": "3.8.15 (default, Nov 24 2022, 15:19:38) \n[GCC 11.2.0]", "command_line_arguments": "/home/beebeaver/anaconda3/envs/gym-env8/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.5", "end_time_seconds": "1670424019" }, "total": 822.4613590510007, "count": 1, "self": 0.32184880599925236, "children": { "run_training.setup": { "total": 0.027923273000851623, "count": 1, "self": 0.027923273000851623 }, "TrainerController.start_learning": { "total": 822.1115869720006, "count": 1, "self": 0.7508249988259195, "children": { "TrainerController._reset_env": { "total": 3.6354277279997405, "count": 1, "self": 3.6354277279997405 }, "TrainerController.advance": { "total": 817.6527711431754, "count": 31664, "self": 0.7261646283750451, "children": { "env_step": { "total": 507.2563535300478, "count": 31664, "self": 449.7314077909168, "children": { "SubprocessEnvManager._take_step": { "total": 57.010682805002034, "count": 31664, "self": 2.1758805517674773, "children": { "TorchPolicy.evaluate": { "total": 54.83480225323456, "count": 31304, "self": 18.488256247192112, "children": { "TorchPolicy.sample_actions": { "total": 36.346546006042445, "count": 31304, "self": 36.346546006042445 } } } } }, "workers": { "total": 0.5142629341289648, "count": 31664, "self": 0.0, "children": { "worker_root": { "total": 820.5205130549857, "count": 31664, "is_parallel": true, "self": 421.69939964108016, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017770320000636275, "count": 1, "is_parallel": true, "self": 0.0006272190003073774, "children": { "_process_rank_one_or_two_observation": { "total": 0.00114981299975625, "count": 8, "is_parallel": true, "self": 0.00114981299975625 } } }, "UnityEnvironment.step": { "total": 0.03242487099942082, "count": 1, "is_parallel": true, "self": 0.0002637229990796186, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002905310002461192, "count": 1, "is_parallel": true, "self": 0.0002905310002461192 }, "communicator.exchange": { "total": 0.030962662000092678, "count": 1, "is_parallel": true, "self": 0.030962662000092678 }, "steps_from_proto": { "total": 0.0009079550000024028, "count": 1, "is_parallel": true, "self": 0.0002472199985277257, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006607350014746771, "count": 8, "is_parallel": true, "self": 0.0006607350014746771 } } } } } } }, "UnityEnvironment.step": { "total": 398.82111341390555, "count": 31663, "is_parallel": true, "self": 8.969826948105947, "children": { "UnityEnvironment._generate_step_input": { "total": 6.6911876690383, "count": 31663, "is_parallel": true, "self": 6.6911876690383 }, "communicator.exchange": { "total": 352.9570988569576, "count": 31663, "is_parallel": true, "self": 352.9570988569576 }, "steps_from_proto": { "total": 30.202999939803703, "count": 31663, "is_parallel": true, "self": 7.704299847459879, "children": { "_process_rank_one_or_two_observation": { "total": 22.498700092343825, "count": 253304, "is_parallel": true, "self": 22.498700092343825 } } } } } } } } } } }, "trainer_advance": { "total": 309.67025298475255, "count": 31664, "self": 1.3033199455676368, "children": { "process_trajectory": { "total": 63.41054487620113, "count": 31664, "self": 63.2446436752025, "children": { "RLTrainer._checkpoint": { "total": 0.1659012009986327, "count": 1, "self": 0.1659012009986327 } } }, "_update_policy": { "total": 244.95638816298379, "count": 222, "self": 98.08771483411147, "children": { "TorchPPOOptimizer.update": { "total": 146.86867332887232, "count": 11361, "self": 146.86867332887232 } } } } } } }, "trainer_threads": { "total": 1.1129995982628316e-06, "count": 1, "self": 1.1129995982628316e-06 }, "TrainerController._save_models": { "total": 0.0725619889999507, "count": 1, "self": 0.001673331000347389, "children": { "RLTrainer._checkpoint": { "total": 0.07088865799960331, "count": 1, "self": 0.07088865799960331 } } } } } } }