{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8627583384513855, "min": 0.8627583384513855, "max": 1.4661074876785278, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 26227.853515625, "min": 26227.853515625, "max": 44475.8359375, "count": 3 }, "Pyramids.Step.mean": { "value": 89940.0, "min": 29971.0, "max": 89940.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89940.0, "min": 29971.0, "max": 89940.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.026404783129692078, "min": -0.1570538729429245, "max": -0.026404783129692078, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -6.416362285614014, "min": -37.378822326660156, "max": -6.416362285614014, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1960386037826538, "min": 0.1960386037826538, "max": 0.2951323986053467, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 47.63738250732422, "min": 47.63738250732422, "max": 71.12690734863281, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06842469821153468, "min": 0.06829189118804865, "max": 0.07134880159548844, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8895210767499508, "min": 0.5707904127639075, "max": 0.8895210767499508, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0049486540780687245, "min": 0.0015458890939535521, "max": 0.010129113229843223, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.06433250301489342, "min": 0.017004780033489073, "max": 0.08103290583874578, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.764676642546154e-05, "min": 7.764676642546154e-05, "max": 0.000248515892161375, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0010094079635310001, "min": 0.0010094079635310001, "max": 0.001988127137291, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12588223076923077, "min": 0.12588223076923077, "max": 0.182838625, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.636469, "min": 1.462709, "max": 1.709471, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.002595634853846154, "min": 0.002595634853846154, "max": 0.008285578637499999, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0337432531, "min": 0.0337432531, "max": 0.06628462909999999, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.13922631740570068, "min": 0.13922631740570068, "max": 0.5307154655456543, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.8099421262741089, "min": 1.8099421262741089, "max": 4.245723724365234, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 877.4117647058823, "min": 877.4117647058823, "max": 974.7352941176471, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29832.0, "min": 17153.0, "max": 33141.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.4075353380073519, "min": -0.8579941663671943, "max": -0.4075353380073519, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -13.856201492249966, "min": -29.171801656484604, "max": -13.16900086402893, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.4075353380073519, "min": -0.8579941663671943, "max": -0.4075353380073519, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -13.856201492249966, "min": -29.171801656484604, "max": -13.16900086402893, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.3887475881013362, "min": 1.3887475881013362, "max": 10.46947684801287, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 47.21741799544543, "min": 47.21741799544543, "max": 188.45058326423168, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725552434", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725552756" }, "total": 322.095626413, "count": 1, "self": 0.6295408580000412, "children": { "run_training.setup": { "total": 0.07744718300000386, "count": 1, "self": 0.07744718300000386 }, "TrainerController.start_learning": { "total": 321.38863837199995, "count": 1, "self": 0.23017324900263247, "children": { "TrainerController._reset_env": { "total": 2.429557453999905, "count": 1, "self": 2.429557453999905 }, "TrainerController.advance": { "total": 318.62210449199733, "count": 6324, "self": 0.26900457400461164, "children": { "env_step": { "total": 198.15954763399964, "count": 6324, "self": 180.56680035500517, "children": { "SubprocessEnvManager._take_step": { "total": 17.434732251996365, "count": 6324, "self": 0.7881716449879832, "children": { "TorchPolicy.evaluate": { "total": 16.646560607008382, "count": 6302, "self": 16.646560607008382 } } }, "workers": { "total": 0.15801502699810044, "count": 6324, "self": 0.0, "children": { "worker_root": { "total": 320.6044895869991, "count": 6324, "is_parallel": true, "self": 159.1514349330015, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031883149999885063, "count": 1, "is_parallel": true, "self": 0.0010821649999570582, "children": { "_process_rank_one_or_two_observation": { "total": 0.002106150000031448, "count": 8, "is_parallel": true, "self": 0.002106150000031448 } } }, "UnityEnvironment.step": { "total": 0.06683837399998538, "count": 1, "is_parallel": true, "self": 0.0007921289999330838, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005262480000283176, "count": 1, "is_parallel": true, "self": 0.0005262480000283176 }, "communicator.exchange": { "total": 0.06344701099999384, "count": 1, "is_parallel": true, "self": 0.06344701099999384 }, "steps_from_proto": { "total": 0.0020729860000301414, "count": 1, "is_parallel": true, "self": 0.00041600200006541854, "children": { "_process_rank_one_or_two_observation": { "total": 0.001656983999964723, "count": 8, "is_parallel": true, "self": 0.001656983999964723 } } } } } } }, "UnityEnvironment.step": { "total": 161.45305465399758, "count": 6323, "is_parallel": true, "self": 5.304709088989057, "children": { "UnityEnvironment._generate_step_input": { "total": 3.2025543060098016, "count": 6323, "is_parallel": true, "self": 3.2025543060098016 }, "communicator.exchange": { "total": 139.6412388779928, "count": 6323, "is_parallel": true, "self": 139.6412388779928 }, "steps_from_proto": { "total": 13.30455238100592, "count": 6323, "is_parallel": true, "self": 2.8828215469986844, "children": { "_process_rank_one_or_two_observation": { "total": 10.421730834007235, "count": 50584, "is_parallel": true, "self": 10.421730834007235 } } } } } } } } } } }, "trainer_advance": { "total": 120.19355228399309, "count": 6324, "self": 0.35920689000056427, "children": { "process_trajectory": { "total": 17.931157586993322, "count": 6324, "self": 17.931157586993322 }, "_update_policy": { "total": 101.9031878069992, "count": 37, "self": 40.53082022799572, "children": { "TorchPPOOptimizer.update": { "total": 61.37236757900348, "count": 2298, "self": 61.37236757900348 } } } } } } }, "trainer_threads": { "total": 1.0260000635753386e-06, "count": 1, "self": 1.0260000635753386e-06 }, "TrainerController._save_models": { "total": 0.10680215100001078, "count": 1, "self": 0.002007389000027615, "children": { "RLTrainer._checkpoint": { "total": 0.10479476199998317, "count": 1, "self": 0.10479476199998317 } } } } } } }