{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6408494710922241, "min": 0.6408494710922241, "max": 1.4861477613449097, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19297.259765625, "min": 19117.44140625, "max": 45083.77734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19283650815486908, "min": -0.10307580232620239, "max": 0.2418624311685562, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 49.173309326171875, "min": -24.94434356689453, "max": 62.64236831665039, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.001977069303393364, "min": -0.001977069303393364, "max": 0.2115447074174881, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5041526556015015, "min": -0.5041526556015015, "max": 50.770729064941406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06590539743709894, "min": 0.06590539743709894, "max": 0.07499024733672432, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9885809615564842, "min": 0.49030235925543486, "max": 1.0528852293791715, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010258936074549436, "min": 8.5625140378829e-05, "max": 0.01108743599076663, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15388404111824153, "min": 0.001027501684545948, "max": 0.1575687842875292, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4284975238666686e-06, "min": 7.4284975238666686e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011142746285800003, "min": 0.00011142746285800003, "max": 0.0033775993741336, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247613333333334, "min": 0.10247613333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371420000000002, "min": 1.3691136000000002, "max": 2.4258664000000008, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025736572000000006, "min": 0.00025736572000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038604858000000006, "min": 0.0038604858000000006, "max": 0.11260405336000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011012685485184193, "min": 0.011012685485184193, "max": 0.30699676275253296, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16519027948379517, "min": 0.15641044080257416, "max": 2.148977279663086, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 644.1923076923077, "min": 572.4565217391304, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33498.0, "min": 15984.0, "max": 33498.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7578705572614483, "min": -1.0000000521540642, "max": 0.9569079712033272, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 38.65139842033386, "min": -32.000001668930054, "max": 49.30439821630716, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7578705572614483, "min": -1.0000000521540642, "max": 0.9569079712033272, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 38.65139842033386, "min": -32.000001668930054, "max": 49.30439821630716, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07410621859690211, "min": 0.06647874598686189, "max": 5.811543075367808, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7794171484420076, "min": 3.0580223153956467, "max": 92.98468920588493, "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": "1690484910", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690487249" }, "total": 2338.751021056, "count": 1, "self": 0.9807321169996612, "children": { "run_training.setup": { "total": 0.04888544599998568, "count": 1, "self": 0.04888544599998568 }, "TrainerController.start_learning": { "total": 2337.7214034930003, "count": 1, "self": 1.6228117659561576, "children": { "TrainerController._reset_env": { "total": 5.363579864000258, "count": 1, "self": 5.363579864000258 }, "TrainerController.advance": { "total": 2330.580092631044, "count": 63256, "self": 1.5952832280481744, "children": { "env_step": { "total": 1668.247859065054, "count": 63256, "self": 1545.552998537075, "children": { "SubprocessEnvManager._take_step": { "total": 121.71415491289281, "count": 63256, "self": 5.266367813888337, "children": { "TorchPolicy.evaluate": { "total": 116.44778709900447, "count": 62564, "self": 116.44778709900447 } } }, "workers": { "total": 0.9807056150862081, "count": 63256, "self": 0.0, "children": { "worker_root": { "total": 2331.7810512981305, "count": 63256, "is_parallel": true, "self": 915.8020694082161, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026223300001220196, "count": 1, "is_parallel": true, "self": 0.0007190379997155105, "children": { "_process_rank_one_or_two_observation": { "total": 0.001903292000406509, "count": 8, "is_parallel": true, "self": 0.001903292000406509 } } }, "UnityEnvironment.step": { "total": 0.050606782000159, "count": 1, "is_parallel": true, "self": 0.0006003959997542552, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000544510000054288, "count": 1, "is_parallel": true, "self": 0.000544510000054288 }, "communicator.exchange": { "total": 0.047274241000195616, "count": 1, "is_parallel": true, "self": 0.047274241000195616 }, "steps_from_proto": { "total": 0.0021876350001548417, "count": 1, "is_parallel": true, "self": 0.00041316500028187875, "children": { "_process_rank_one_or_two_observation": { "total": 0.001774469999872963, "count": 8, "is_parallel": true, "self": 0.001774469999872963 } } } } } } }, "UnityEnvironment.step": { "total": 1415.9789818899144, "count": 63255, "is_parallel": true, "self": 35.6191070227419, "children": { "UnityEnvironment._generate_step_input": { "total": 24.967103598030462, "count": 63255, "is_parallel": true, "self": 24.967103598030462 }, "communicator.exchange": { "total": 1243.7901425280884, "count": 63255, "is_parallel": true, "self": 1243.7901425280884 }, "steps_from_proto": { "total": 111.60262874105365, "count": 63255, "is_parallel": true, "self": 23.652295668001443, "children": { "_process_rank_one_or_two_observation": { "total": 87.9503330730522, "count": 506040, "is_parallel": true, "self": 87.9503330730522 } } } } } } } } } } }, "trainer_advance": { "total": 660.7369503379418, "count": 63256, "self": 2.850587423950401, "children": { "process_trajectory": { "total": 117.1876376759974, "count": 63256, "self": 116.90508062799836, "children": { "RLTrainer._checkpoint": { "total": 0.2825570479990347, "count": 2, "self": 0.2825570479990347 } } }, "_update_policy": { "total": 540.698725237994, "count": 437, "self": 354.1733642209733, "children": { "TorchPPOOptimizer.update": { "total": 186.5253610170207, "count": 22830, "self": 186.5253610170207 } } } } } } }, "trainer_threads": { "total": 1.6770000001997687e-06, "count": 1, "self": 1.6770000001997687e-06 }, "TrainerController._save_models": { "total": 0.15491755499988358, "count": 1, "self": 0.001879200000075798, "children": { "RLTrainer._checkpoint": { "total": 0.15303835499980778, "count": 1, "self": 0.15303835499980778 } } } } } } }