{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5284208059310913, "min": 0.5284208059310913, "max": 1.4849109649658203, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15869.533203125, "min": 15869.533203125, "max": 45046.2578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4880548119544983, "min": -0.08041174709796906, "max": 0.5582343339920044, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.2867431640625, "min": -19.379230499267578, "max": 153.51443481445312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03111603483557701, "min": -0.004508709069341421, "max": 0.3195103108882904, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.370213508605957, "min": -1.1948078870773315, "max": 75.72394561767578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06480169403302069, "min": 0.06464056181856719, "max": 0.07471829460554232, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9720254104953103, "min": 0.4971419343719495, "max": 1.0460561244775923, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012113029369114276, "min": 0.0003495639108002467, "max": 0.01632132755046422, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18169544053671416, "min": 0.00314607519720222, "max": 0.22849858570649909, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5278774907399975e-06, "min": 7.5278774907399975e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011291816236109997, "min": 0.00011291816236109997, "max": 0.0032584784138406, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250926000000002, "min": 0.10250926000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376389000000004, "min": 1.3886848, "max": 2.4860916, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002606750739999999, "min": 0.0002606750739999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003910126109999999, "min": 0.003910126109999999, "max": 0.10864055084000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01451638713479042, "min": 0.01451638713479042, "max": 0.34321460127830505, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2177458107471466, "min": 0.2090751826763153, "max": 2.4025022983551025, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 378.05, "min": 344.6385542168675, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30244.0, "min": 15984.0, "max": 32369.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5218474868685008, "min": -1.0000000521540642, "max": 1.6291058681467, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 121.74779894948006, "min": -31.998401656746864, "max": 138.4739987924695, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5218474868685008, "min": -1.0000000521540642, "max": 1.6291058681467, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 121.74779894948006, "min": -31.998401656746864, "max": 138.4739987924695, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.055966997491486835, "min": 0.0536967123971622, "max": 6.505170843563974, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.477359799318947, "min": 4.477359799318947, "max": 104.08273349702358, "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": "1752595067", "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": "1752597457" }, "total": 2389.834612516, "count": 1, "self": 0.536401202999059, "children": { "run_training.setup": { "total": 0.02104367100014315, "count": 1, "self": 0.02104367100014315 }, "TrainerController.start_learning": { "total": 2389.2771676420007, "count": 1, "self": 1.5829970000195317, "children": { "TrainerController._reset_env": { "total": 2.375355157000058, "count": 1, "self": 2.375355157000058 }, "TrainerController.advance": { "total": 2385.2259904179805, "count": 63760, "self": 1.721807648038066, "children": { "env_step": { "total": 1679.3813456739715, "count": 63760, "self": 1509.6298870460641, "children": { "SubprocessEnvManager._take_step": { "total": 168.73279918102548, "count": 63760, "self": 5.051166997004884, "children": { "TorchPolicy.evaluate": { "total": 163.6816321840206, "count": 62574, "self": 163.6816321840206 } } }, "workers": { "total": 1.018659446881884, "count": 63760, "self": 0.0, "children": { "worker_root": { "total": 2381.4236291319394, "count": 63760, "is_parallel": true, "self": 1001.4106096558321, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020314489997872442, "count": 1, "is_parallel": true, "self": 0.0006350929995733168, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013963560002139275, "count": 8, "is_parallel": true, "self": 0.0013963560002139275 } } }, "UnityEnvironment.step": { "total": 0.10839608599985695, "count": 1, "is_parallel": true, "self": 0.0005547029998069775, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004673649998494511, "count": 1, "is_parallel": true, "self": 0.0004673649998494511 }, "communicator.exchange": { "total": 0.10561517300016021, "count": 1, "is_parallel": true, "self": 0.10561517300016021 }, "steps_from_proto": { "total": 0.00175884500004031, "count": 1, "is_parallel": true, "self": 0.0003555650000635069, "children": { "_process_rank_one_or_two_observation": { "total": 0.001403279999976803, "count": 8, "is_parallel": true, "self": 0.001403279999976803 } } } } } } }, "UnityEnvironment.step": { "total": 1380.0130194761073, "count": 63759, "is_parallel": true, "self": 34.69901654918772, "children": { "UnityEnvironment._generate_step_input": { "total": 25.70651782400728, "count": 63759, "is_parallel": true, "self": 25.70651782400728 }, "communicator.exchange": { "total": 1210.7029252979235, "count": 63759, "is_parallel": true, "self": 1210.7029252979235 }, "steps_from_proto": { "total": 108.90455980498882, "count": 63759, "is_parallel": true, "self": 23.05567895506556, "children": { "_process_rank_one_or_two_observation": { "total": 85.84888084992326, "count": 510072, "is_parallel": true, "self": 85.84888084992326 } } } } } } } } } } }, "trainer_advance": { "total": 704.1228370959709, "count": 63760, "self": 2.8584653739649184, "children": { "process_trajectory": { "total": 136.8139476780127, "count": 63760, "self": 136.6036074510123, "children": { "RLTrainer._checkpoint": { "total": 0.21034022700041533, "count": 2, "self": 0.21034022700041533 } } }, "_update_policy": { "total": 564.4504240439933, "count": 443, "self": 316.2543889019546, "children": { "TorchPPOOptimizer.update": { "total": 248.19603514203868, "count": 22803, "self": 248.19603514203868 } } } } } } }, "trainer_threads": { "total": 1.1130005077575333e-06, "count": 1, "self": 1.1130005077575333e-06 }, "TrainerController._save_models": { "total": 0.09282395399986854, "count": 1, "self": 0.0012350710003374843, "children": { "RLTrainer._checkpoint": { "total": 0.09158888299953105, "count": 1, "self": 0.09158888299953105 } } } } } } }