{ "name": "root", "gauges": { "PushBlock.Policy.Entropy.mean": { "value": 0.5057125091552734, "min": 0.5057125091552734, "max": 1.8453508615493774, "count": 16 }, "PushBlock.Policy.Entropy.sum": { "value": 30342.751953125, "min": 30342.751953125, "max": 111961.125, "count": 16 }, "PushBlock.Step.mean": { "value": 959987.0, "min": 59968.0, "max": 959987.0, "count": 16 }, "PushBlock.Step.sum": { "value": 959987.0, "min": 59968.0, "max": 959987.0, "count": 16 }, "PushBlock.Policy.ExtrinsicValueEstimate.mean": { "value": 3.3463761806488037, "min": -0.10228154063224792, "max": 3.5732831954956055, "count": 16 }, "PushBlock.Policy.ExtrinsicValueEstimate.sum": { "value": 5263.849609375, "min": -97.065185546875, "max": 5828.02490234375, "count": 16 }, "PushBlock.Losses.PolicyLoss.mean": { "value": 0.07074756970315979, "min": 0.06713354328430483, "max": 0.07087487300647818, "count": 16 }, "PushBlock.Losses.PolicyLoss.sum": { "value": 2.051679521391634, "min": 0.96914859500248, "max": 2.055371317187867, "count": 16 }, "PushBlock.Losses.ValueLoss.mean": { "value": 0.30664365344156314, "min": 0.0007856689771078925, "max": 0.3977642041461654, "count": 16 }, "PushBlock.Losses.ValueLoss.sum": { "value": 8.89266594980533, "min": 0.010999365679510495, "max": 11.535161920238798, "count": 16 }, "PushBlock.Policy.LearningRate.mean": { "value": 2.0788634449796547e-05, "min": 2.0788634449796547e-05, "max": 0.00029089920303360003, "count": 16 }, "PushBlock.Policy.LearningRate.sum": { "value": 0.0006028703990440999, "min": 0.0006028703990440999, "max": 0.0071437558187481985, "count": 16 }, "PushBlock.Policy.Epsilon.mean": { "value": 0.10692951379310346, "min": 0.10692951379310346, "max": 0.19696639999999999, "count": 16 }, "PushBlock.Policy.Epsilon.sum": { "value": 3.1009559, "min": 2.7575296, "max": 5.1917718000000015, "count": 16 }, "PushBlock.Policy.Beta.mean": { "value": 0.0007022584279310345, "min": 0.0007022584279310345, "max": 0.00969694336, "count": 16 }, "PushBlock.Policy.Beta.sum": { "value": 0.02036549441, "min": 0.02036549441, "max": 0.23816705482, "count": 16 }, "PushBlock.Environment.EpisodeLength.mean": { "value": 52.71301247771836, "min": 49.440097799511, "max": 999.0, "count": 16 }, "PushBlock.Environment.EpisodeLength.sum": { "value": 59144.0, "min": 31968.0, "max": 71018.0, "count": 16 }, "PushBlock.Environment.CumulativeReward.mean": { "value": 4.857366297034813, "min": -1.0000000447034836, "max": 4.892981806867043, "count": 16 }, "PushBlock.Environment.CumulativeReward.sum": { "value": 5440.25025267899, "min": -32.000001430511475, "max": 6008.581658832729, "count": 16 }, "PushBlock.Policy.ExtrinsicReward.mean": { "value": 4.857366297034813, "min": -1.0000000447034836, "max": 4.892981806867043, "count": 16 }, "PushBlock.Policy.ExtrinsicReward.sum": { "value": 5440.25025267899, "min": -32.000001430511475, "max": 6008.581658832729, "count": 16 }, "PushBlock.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "PushBlock.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723125498", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./training-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723126584" }, "total": 1086.102436561, "count": 1, "self": 0.44057384799998545, "children": { "run_training.setup": { "total": 0.05948779099992407, "count": 1, "self": 0.05948779099992407 }, "TrainerController.start_learning": { "total": 1085.602374922, "count": 1, "self": 0.8571807120065387, "children": { "TrainerController._reset_env": { "total": 3.146449375999964, "count": 1, "self": 3.146449375999964 }, "TrainerController.advance": { "total": 1081.5469878759936, "count": 39374, "self": 0.9223190180264282, "children": { "env_step": { "total": 651.7303850059682, "count": 39374, "self": 588.8443498189744, "children": { "SubprocessEnvManager._take_step": { "total": 62.403319629999146, "count": 39374, "self": 2.721327139013283, "children": { "TorchPolicy.evaluate": { "total": 59.68199249098586, "count": 31275, "self": 59.68199249098586 } } }, "workers": { "total": 0.4827155569946626, "count": 39374, "self": 0.0, "children": { "worker_root": { "total": 1083.5189153969945, "count": 39374, "is_parallel": true, "self": 573.9133127020157, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008095230999970227, "count": 1, "is_parallel": true, "self": 0.006371104999971067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017241259999991598, "count": 4, "is_parallel": true, "self": 0.0017241259999991598 } } }, "UnityEnvironment.step": { "total": 0.035432894999985365, "count": 1, "is_parallel": true, "self": 0.000876696000091215, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007195549999323703, "count": 1, "is_parallel": true, "self": 0.0007195549999323703 }, "communicator.exchange": { "total": 0.031510185999991336, "count": 1, "is_parallel": true, "self": 0.031510185999991336 }, "steps_from_proto": { "total": 0.0023264579999704438, "count": 1, "is_parallel": true, "self": 0.0003776250000555592, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019488329999148846, "count": 4, "is_parallel": true, "self": 0.0019488329999148846 } } } } } } }, "UnityEnvironment.step": { "total": 509.60560269497887, "count": 39373, "is_parallel": true, "self": 25.173398205975104, "children": { "UnityEnvironment._generate_step_input": { "total": 19.87260991800565, "count": 39373, "is_parallel": true, "self": 19.87260991800565 }, "communicator.exchange": { "total": 393.24340439598996, "count": 39373, "is_parallel": true, "self": 393.24340439598996 }, "steps_from_proto": { "total": 71.31619017500816, "count": 39373, "is_parallel": true, "self": 11.643081277982674, "children": { "_process_rank_one_or_two_observation": { "total": 59.673108897025486, "count": 157492, "is_parallel": true, "self": 59.673108897025486 } } } } } } } } } } }, "trainer_advance": { "total": 428.89428385199915, "count": 39374, "self": 1.8710544049820328, "children": { "process_trajectory": { "total": 102.43821347601931, "count": 39374, "self": 102.22136047201946, "children": { "RLTrainer._checkpoint": { "total": 0.21685300399985863, "count": 2, "self": 0.21685300399985863 } } }, "_update_policy": { "total": 324.5850159709978, "count": 457, "self": 146.49035086501215, "children": { "TorchPPOOptimizer.update": { "total": 178.09466510598565, "count": 23061, "self": 178.09466510598565 } } } } } } }, "trainer_threads": { "total": 9.670000054029515e-07, "count": 1, "self": 9.670000054029515e-07 }, "TrainerController._save_models": { "total": 0.05175599099993633, "count": 1, "self": 0.0007589500000904081, "children": { "RLTrainer._checkpoint": { "total": 0.05099704099984592, "count": 1, "self": 0.05099704099984592 } } } } } } }