{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4935741126537323, "min": 0.4935741126537323, "max": 1.467158317565918, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14751.943359375, "min": 14751.943359375, "max": 44507.71484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5647760033607483, "min": -0.08042053878307343, "max": 0.5647760033607483, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.4429473876953, "min": -19.381349563598633, "max": 156.4429473876953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.07561420649290085, "min": -0.07561420649290085, "max": 0.2936772406101227, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -20.94513511657715, "min": -20.94513511657715, "max": 70.48253631591797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.070965174417602, "min": 0.06495135207531146, "max": 0.07382341051771718, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.993512441846428, "min": 0.47700984054445766, "max": 1.1073511577657578, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.025176059511664295, "min": 0.0008474972185009295, "max": 0.025176059511664295, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.35246483316330013, "min": 0.005932480529506507, "max": 0.35246483316330013, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.28480471462143e-06, "min": 7.28480471462143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010198726600470002, "min": 0.00010198726600470002, "max": 0.0035070968309678, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242823571428572, "min": 0.10242823571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339953, "min": 1.3691136000000002, "max": 2.5690322000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025258074785714294, "min": 0.00025258074785714294, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035361304700000013, "min": 0.0035361304700000013, "max": 0.11692631678000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008750544860959053, "min": 0.00849044881761074, "max": 0.5230200290679932, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12250763177871704, "min": 0.11886627972126007, "max": 3.661140203475952, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.40697674418607, "min": 329.40697674418607, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28329.0, "min": 15984.0, "max": 33568.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6722823395448572, "min": -1.0000000521540642, "max": 1.6722823395448572, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.14399886131287, "min": -32.000001668930054, "max": 142.14399886131287, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6722823395448572, "min": -1.0000000521540642, "max": 1.6722823395448572, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.14399886131287, "min": -32.000001668930054, "max": 142.14399886131287, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030229675734538913, "min": 0.030229675734538913, "max": 11.100240192376077, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5695224374358077, "min": 2.5695224374358077, "max": 177.60384307801723, "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": "1701516215", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/opt/conda/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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701518720" }, "total": 2505.304226058, "count": 1, "self": 0.38100207599973146, "children": { "run_training.setup": { "total": 0.09773542300013105, "count": 1, "self": 0.09773542300013105 }, "TrainerController.start_learning": { "total": 2504.825488559, "count": 1, "self": 1.636165807953148, "children": { "TrainerController._reset_env": { "total": 2.750886860999799, "count": 1, "self": 2.750886860999799 }, "TrainerController.advance": { "total": 2500.364389289047, "count": 63677, "self": 1.694592466064023, "children": { "env_step": { "total": 1609.357019011958, "count": 63677, "self": 1483.6055631649015, "children": { "SubprocessEnvManager._take_step": { "total": 124.72657889706738, "count": 63677, "self": 5.280796016091472, "children": { "TorchPolicy.evaluate": { "total": 119.44578288097591, "count": 62557, "self": 119.44578288097591 } } }, "workers": { "total": 1.0248769499892205, "count": 63677, "self": 0.0, "children": { "worker_root": { "total": 2502.1594690359657, "count": 63677, "is_parallel": true, "self": 1148.875177171908, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002381091999950513, "count": 1, "is_parallel": true, "self": 0.0007242210006097594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016568709993407538, "count": 8, "is_parallel": true, "self": 0.0016568709993407538 } } }, "UnityEnvironment.step": { "total": 0.03902450999999019, "count": 1, "is_parallel": true, "self": 0.00042446399993423256, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004501749999690219, "count": 1, "is_parallel": true, "self": 0.0004501749999690219 }, "communicator.exchange": { "total": 0.03670142200007831, "count": 1, "is_parallel": true, "self": 0.03670142200007831 }, "steps_from_proto": { "total": 0.0014484490000086225, "count": 1, "is_parallel": true, "self": 0.00031598000009580574, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011324689999128168, "count": 8, "is_parallel": true, "self": 0.0011324689999128168 } } } } } } }, "UnityEnvironment.step": { "total": 1353.2842918640576, "count": 63676, "is_parallel": true, "self": 29.068680306120996, "children": { "UnityEnvironment._generate_step_input": { "total": 24.68096147993151, "count": 63676, "is_parallel": true, "self": 24.68096147993151 }, "communicator.exchange": { "total": 1199.4893243349823, "count": 63676, "is_parallel": true, "self": 1199.4893243349823 }, "steps_from_proto": { "total": 100.04532574302289, "count": 63676, "is_parallel": true, "self": 20.499260584999774, "children": { "_process_rank_one_or_two_observation": { "total": 79.54606515802311, "count": 509408, "is_parallel": true, "self": 79.54606515802311 } } } } } } } } } } }, "trainer_advance": { "total": 889.3127778110247, "count": 63677, "self": 3.186108067023497, "children": { "process_trajectory": { "total": 155.82249490900745, "count": 63677, "self": 155.6665104930073, "children": { "RLTrainer._checkpoint": { "total": 0.15598441600013757, "count": 2, "self": 0.15598441600013757 } } }, "_update_policy": { "total": 730.3041748349938, "count": 449, "self": 446.9584316469975, "children": { "TorchPPOOptimizer.update": { "total": 283.3457431879963, "count": 22848, "self": 283.3457431879963 } } } } } } }, "trainer_threads": { "total": 1.1830002222268376e-06, "count": 1, "self": 1.1830002222268376e-06 }, "TrainerController._save_models": { "total": 0.07404541799996878, "count": 1, "self": 0.0015703580002082163, "children": { "RLTrainer._checkpoint": { "total": 0.07247505999976056, "count": 1, "self": 0.07247505999976056 } } } } } } }