{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5592962503433228, "min": 0.5592962503433228, "max": 1.488551378250122, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16626.759765625, "min": 16626.759765625, "max": 45156.6953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2996983230113983, "min": -0.12234305590391159, "max": 0.3224586546421051, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 77.62186431884766, "min": -28.995304107666016, "max": 83.1943359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03845490142703056, "min": -0.02664370834827423, "max": 0.20508146286010742, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.959819793701172, "min": -6.874076843261719, "max": 49.21955108642578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06977603335690218, "min": 0.06600544648913469, "max": 0.0747686346025739, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9768644669966305, "min": 0.49412942926824927, "max": 1.0886102704680525, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011730213324404933, "min": 9.314517930524923e-05, "max": 0.013185607008289798, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16422298654166906, "min": 0.0013040325102734892, "max": 0.19778410512434696, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.41830467012143e-06, "min": 7.41830467012143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010385626538170002, "min": 0.00010385626538170002, "max": 0.0035073806308731996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247273571428574, "min": 0.10247273571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346183000000003, "min": 1.3886848, "max": 2.5691268, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025702629785714296, "min": 0.00025702629785714296, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035983681700000013, "min": 0.0035983681700000013, "max": 0.11693576732, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010160906240344048, "min": 0.010160906240344048, "max": 0.31833595037460327, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14225268363952637, "min": 0.14225268363952637, "max": 2.228351593017578, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 518.6545454545454, "min": 469.3709677419355, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28526.0, "min": 15984.0, "max": 32777.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.050910688670618, "min": -1.0000000521540642, "max": 1.2677967018279872, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 58.85099856555462, "min": -31.993601694703102, "max": 77.33559881150723, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.050910688670618, "min": -1.0000000521540642, "max": 1.2677967018279872, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 58.85099856555462, "min": -31.993601694703102, "max": 77.33559881150723, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.054595591822622476, "min": 0.05441278382586163, "max": 5.991612376179546, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0573531420668587, "min": 3.0573531420668587, "max": 95.86579801887274, "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": "1750962185", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750964263" }, "total": 2078.23589981, "count": 1, "self": 0.47650225099960153, "children": { "run_training.setup": { "total": 0.02053994400012016, "count": 1, "self": 0.02053994400012016 }, "TrainerController.start_learning": { "total": 2077.738857615, "count": 1, "self": 1.5060284169971965, "children": { "TrainerController._reset_env": { "total": 2.209129562999806, "count": 1, "self": 2.209129562999806 }, "TrainerController.advance": { "total": 2073.9354192530036, "count": 63436, "self": 1.6473600240015003, "children": { "env_step": { "total": 1414.2889575840068, "count": 63436, "self": 1255.3645143130434, "children": { "SubprocessEnvManager._take_step": { "total": 157.982766107958, "count": 63436, "self": 4.885343346932132, "children": { "TorchPolicy.evaluate": { "total": 153.09742276102588, "count": 62563, "self": 153.09742276102588 } } }, "workers": { "total": 0.9416771630053518, "count": 63436, "self": 0.0, "children": { "worker_root": { "total": 2072.162575700115, "count": 63436, "is_parallel": true, "self": 936.1511449120871, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017457019998801115, "count": 1, "is_parallel": true, "self": 0.0005794009998680849, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011663010000120266, "count": 8, "is_parallel": true, "self": 0.0011663010000120266 } } }, "UnityEnvironment.step": { "total": 0.050244622999798594, "count": 1, "is_parallel": true, "self": 0.0005376389995035424, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046733799990761327, "count": 1, "is_parallel": true, "self": 0.00046733799990761327 }, "communicator.exchange": { "total": 0.047599681000065175, "count": 1, "is_parallel": true, "self": 0.047599681000065175 }, "steps_from_proto": { "total": 0.0016399650003222632, "count": 1, "is_parallel": true, "self": 0.0003568640004232293, "children": { "_process_rank_one_or_two_observation": { "total": 0.001283100999899034, "count": 8, "is_parallel": true, "self": 0.001283100999899034 } } } } } } }, "UnityEnvironment.step": { "total": 1136.011430788028, "count": 63435, "is_parallel": true, "self": 32.28767071998254, "children": { "UnityEnvironment._generate_step_input": { "total": 22.94445654805895, "count": 63435, "is_parallel": true, "self": 22.94445654805895 }, "communicator.exchange": { "total": 982.3355278130243, "count": 63435, "is_parallel": true, "self": 982.3355278130243 }, "steps_from_proto": { "total": 98.44377570696224, "count": 63435, "is_parallel": true, "self": 20.21586030078379, "children": { "_process_rank_one_or_two_observation": { "total": 78.22791540617845, "count": 507480, "is_parallel": true, "self": 78.22791540617845 } } } } } } } } } } }, "trainer_advance": { "total": 657.9991016449953, "count": 63436, "self": 2.8822895119947134, "children": { "process_trajectory": { "total": 125.48077415300077, "count": 63436, "self": 125.29210968800044, "children": { "RLTrainer._checkpoint": { "total": 0.18866446500032907, "count": 2, "self": 0.18866446500032907 } } }, "_update_policy": { "total": 529.6360379799999, "count": 447, "self": 294.9867392139804, "children": { "TorchPPOOptimizer.update": { "total": 234.64929876601946, "count": 22866, "self": 234.64929876601946 } } } } } } }, "trainer_threads": { "total": 1.1439997251727618e-06, "count": 1, "self": 1.1439997251727618e-06 }, "TrainerController._save_models": { "total": 0.08827923799981363, "count": 1, "self": 0.0016924550000112504, "children": { "RLTrainer._checkpoint": { "total": 0.08658678299980238, "count": 1, "self": 0.08658678299980238 } } } } } } }