{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4622722864151001, "min": 0.4622722864151001, "max": 1.4122027158737183, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13927.33984375, "min": 13927.33984375, "max": 42840.58203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.35350170731544495, "min": -0.10640081763267517, "max": 0.39934098720550537, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 94.38495635986328, "min": -25.536195755004883, "max": 107.42272186279297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.17795561254024506, "min": -0.17795561254024506, "max": 0.4715794324874878, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -47.5141487121582, "min": -47.5141487121582, "max": 113.17906188964844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06763381216421015, "min": 0.06658038241481076, "max": 0.07475794741404432, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9468733702989421, "min": 0.4930598800095338, "max": 1.074437445572888, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019851038272453294, "min": 0.0001938182260281338, "max": 0.019851038272453294, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2779145358143461, "min": 0.0021320004863094716, "max": 0.2779145358143461, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4923617882928594e-06, "min": 7.4923617882928594e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010489306503610003, "min": 0.00010489306503610003, "max": 0.0032555667148112004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249742142857143, "min": 0.10249742142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349639, "min": 1.3691136000000002, "max": 2.4851888000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025949240071428576, "min": 0.00025949240071428576, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036328936100000005, "min": 0.0036328936100000005, "max": 0.10855036112, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016493918374180794, "min": 0.016493918374180794, "max": 0.5968176126480103, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2309148609638214, "min": 0.2309148609638214, "max": 4.177723407745361, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 454.7692307692308, "min": 435.6029411764706, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29560.0, "min": 15984.0, "max": 33389.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3913599745585368, "min": -1.0000000521540642, "max": 1.3913599745585368, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.4383983463049, "min": -32.000001668930054, "max": 90.4383983463049, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3913599745585368, "min": -1.0000000521540642, "max": 1.3913599745585368, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.4383983463049, "min": -32.000001668930054, "max": 90.4383983463049, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07740243841365624, "min": 0.07740243841365624, "max": 11.64180552214384, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.031158496887656, "min": 5.031158496887656, "max": 186.26888835430145, "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": "1749455508", "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": "1749457767" }, "total": 2258.4939164939997, "count": 1, "self": 0.5258019509997212, "children": { "run_training.setup": { "total": 0.019741220000014437, "count": 1, "self": 0.019741220000014437 }, "TrainerController.start_learning": { "total": 2257.948373323, "count": 1, "self": 1.3365377329751027, "children": { "TrainerController._reset_env": { "total": 2.1942436159999943, "count": 1, "self": 2.1942436159999943 }, "TrainerController.advance": { "total": 2254.334103334025, "count": 63489, "self": 1.37891215493255, "children": { "env_step": { "total": 1587.1077853630695, "count": 63489, "self": 1434.6823327779944, "children": { "SubprocessEnvManager._take_step": { "total": 151.65833729303904, "count": 63489, "self": 4.605442787028551, "children": { "TorchPolicy.evaluate": { "total": 147.0528945060105, "count": 62555, "self": 147.0528945060105 } } }, "workers": { "total": 0.7671152920361237, "count": 63489, "self": 0.0, "children": { "worker_root": { "total": 2252.8565510119906, "count": 63489, "is_parallel": true, "self": 930.3695335799537, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018889430000399443, "count": 1, "is_parallel": true, "self": 0.0006038980002358585, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012850449998040858, "count": 8, "is_parallel": true, "self": 0.0012850449998040858 } } }, "UnityEnvironment.step": { "total": 0.0553759430001719, "count": 1, "is_parallel": true, "self": 0.0005180250002467801, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004817110000203684, "count": 1, "is_parallel": true, "self": 0.0004817110000203684 }, "communicator.exchange": { "total": 0.05265008099991064, "count": 1, "is_parallel": true, "self": 0.05265008099991064 }, "steps_from_proto": { "total": 0.0017261259999941103, "count": 1, "is_parallel": true, "self": 0.00035342800015314424, "children": { "_process_rank_one_or_two_observation": { "total": 0.001372697999840966, "count": 8, "is_parallel": true, "self": 0.001372697999840966 } } } } } } }, "UnityEnvironment.step": { "total": 1322.487017432037, "count": 63488, "is_parallel": true, "self": 31.618346542983545, "children": { "UnityEnvironment._generate_step_input": { "total": 22.866671464011915, "count": 63488, "is_parallel": true, "self": 22.866671464011915 }, "communicator.exchange": { "total": 1172.5197741640293, "count": 63488, "is_parallel": true, "self": 1172.5197741640293 }, "steps_from_proto": { "total": 95.48222526101222, "count": 63488, "is_parallel": true, "self": 19.236276070954546, "children": { "_process_rank_one_or_two_observation": { "total": 76.24594919005767, "count": 507904, "is_parallel": true, "self": 76.24594919005767 } } } } } } } } } } }, "trainer_advance": { "total": 665.847405816023, "count": 63489, "self": 2.525921006986664, "children": { "process_trajectory": { "total": 127.4534642450351, "count": 63489, "self": 127.2476142080352, "children": { "RLTrainer._checkpoint": { "total": 0.20585003699989102, "count": 2, "self": 0.20585003699989102 } } }, "_update_policy": { "total": 535.8680205640012, "count": 444, "self": 297.2262207399767, "children": { "TorchPPOOptimizer.update": { "total": 238.64179982402447, "count": 22818, "self": 238.64179982402447 } } } } } } }, "trainer_threads": { "total": 1.2150003385613672e-06, "count": 1, "self": 1.2150003385613672e-06 }, "TrainerController._save_models": { "total": 0.08348742499993023, "count": 1, "self": 0.0013612739999189216, "children": { "RLTrainer._checkpoint": { "total": 0.0821261510000113, "count": 1, "self": 0.0821261510000113 } } } } } } }