{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.591925323009491, "min": 0.5579382181167603, "max": 1.4636337757110596, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17625.16796875, "min": 16666.73046875, "max": 44400.79296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29925.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29925.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19230064749717712, "min": -0.11907154321670532, "max": 0.29784902930259705, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 48.45976257324219, "min": -28.219955444335938, "max": 75.65365600585938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 9.964550971984863, "min": -0.036371611058712006, "max": 10.328259468078613, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2511.06689453125, "min": -9.056530952453613, "max": 2633.7060546875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06901576416057446, "min": 0.0656256905358911, "max": 0.0747430377915791, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9662206982480426, "min": 0.5018770361983889, "max": 1.0802840924094388, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 13.93250840087356, "min": 0.000169167281646334, "max": 13.93250840087356, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 195.05511761222985, "min": 0.002199174661402342, "max": 195.05511761222985, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.601261751992852e-06, "min": 7.601261751992852e-06, "max": 0.0002952340730172143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010641766452789992, "min": 0.00010641766452789992, "max": 0.0036325180891607, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253372142857142, "min": 0.10253372142857142, "max": 0.19841135714285715, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354721, "min": 1.3888795, "max": 2.6108393, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026311877071428553, "min": 0.00026311877071428553, "max": 0.009841294578571427, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036836627899999976, "min": 0.0036836627899999976, "max": 0.12110284606999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012186178006231785, "min": 0.012027187272906303, "max": 0.5746474862098694, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17060649394989014, "min": 0.16838061809539795, "max": 4.0225324630737305, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 702.3720930232558, "min": 530.4464285714286, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30202.0, "min": 16724.0, "max": 33142.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6927999587253083, "min": -0.9999125525355339, "max": 1.1480285501373666, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 29.790398225188255, "min": -31.997201681137085, "max": 64.28959880769253, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6927999587253083, "min": -0.9999125525355339, "max": 1.1480285501373666, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 29.790398225188255, "min": -31.997201681137085, "max": 64.28959880769253, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08960242874021533, "min": 0.0654441894221236, "max": 10.533837996861514, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8529044358292595, "min": 3.6648746076389216, "max": 179.07524594664574, "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": "1715735784", "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": "1715738788" }, "total": 3003.536194075, "count": 1, "self": 0.7113225059997603, "children": { "run_training.setup": { "total": 0.08085487199997488, "count": 1, "self": 0.08085487199997488 }, "TrainerController.start_learning": { "total": 3002.744016697, "count": 1, "self": 2.2361933619581578, "children": { "TrainerController._reset_env": { "total": 3.325425516999985, "count": 1, "self": 3.325425516999985 }, "TrainerController.advance": { "total": 2997.0926982200417, "count": 63284, "self": 2.4201370240871256, "children": { "env_step": { "total": 1945.229080328996, "count": 63284, "self": 1788.983911837956, "children": { "SubprocessEnvManager._take_step": { "total": 154.84697404104708, "count": 63284, "self": 6.962436044008655, "children": { "TorchPolicy.evaluate": { "total": 147.88453799703842, "count": 62544, "self": 147.88453799703842 } } }, "workers": { "total": 1.3981944499927863, "count": 63284, "self": 0.0, "children": { "worker_root": { "total": 2995.703734744967, "count": 63284, "is_parallel": true, "self": 1391.7363884019835, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006754505000003519, "count": 1, "is_parallel": true, "self": 0.004397775000029469, "children": { "_process_rank_one_or_two_observation": { "total": 0.00235672999997405, "count": 8, "is_parallel": true, "self": 0.00235672999997405 } } }, "UnityEnvironment.step": { "total": 0.061622747000001254, "count": 1, "is_parallel": true, "self": 0.0008043980000138617, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005601830000045993, "count": 1, "is_parallel": true, "self": 0.0005601830000045993 }, "communicator.exchange": { "total": 0.058225463999974636, "count": 1, "is_parallel": true, "self": 0.058225463999974636 }, "steps_from_proto": { "total": 0.0020327020000081575, "count": 1, "is_parallel": true, "self": 0.00042591700008642874, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016067849999217287, "count": 8, "is_parallel": true, "self": 0.0016067849999217287 } } } } } } }, "UnityEnvironment.step": { "total": 1603.9673463429833, "count": 63283, "is_parallel": true, "self": 50.32165760195926, "children": { "UnityEnvironment._generate_step_input": { "total": 31.36030527501731, "count": 63283, "is_parallel": true, "self": 31.36030527501731 }, "communicator.exchange": { "total": 1392.9675663019573, "count": 63283, "is_parallel": true, "self": 1392.9675663019573 }, "steps_from_proto": { "total": 129.31781716404953, "count": 63283, "is_parallel": true, "self": 27.895371161086928, "children": { "_process_rank_one_or_two_observation": { "total": 101.4224460029626, "count": 506264, "is_parallel": true, "self": 101.4224460029626 } } } } } } } } } } }, "trainer_advance": { "total": 1049.4434808669587, "count": 63284, "self": 4.3154006939571445, "children": { "process_trajectory": { "total": 162.3012131800033, "count": 63284, "self": 161.9919894070033, "children": { "RLTrainer._checkpoint": { "total": 0.30922377299998516, "count": 2, "self": 0.30922377299998516 } } }, "_update_policy": { "total": 882.8268669929982, "count": 450, "self": 367.5926787890123, "children": { "TorchPPOOptimizer.update": { "total": 515.2341882039859, "count": 22713, "self": 515.2341882039859 } } } } } } }, "trainer_threads": { "total": 1.0580001799098682e-06, "count": 1, "self": 1.0580001799098682e-06 }, "TrainerController._save_models": { "total": 0.08969853999997213, "count": 1, "self": 0.00209417999985817, "children": { "RLTrainer._checkpoint": { "total": 0.08760436000011396, "count": 1, "self": 0.08760436000011396 } } } } } } }