{ "name": "root", "gauges": { "PushBlock.Policy.Entropy.mean": { "value": 0.5864903926849365, "min": 0.5801396369934082, "max": 1.8831936120986938, "count": 33 }, "PushBlock.Policy.Entropy.sum": { "value": 35283.26171875, "min": 34771.25, "max": 114257.125, "count": 33 }, "PushBlock.Environment.EpisodeLength.mean": { "value": 36.3203214695752, "min": 30.37363834422658, "max": 831.9090909090909, "count": 33 }, "PushBlock.Environment.EpisodeLength.sum": { "value": 63270.0, "min": 36604.0, "max": 67947.0, "count": 33 }, "PushBlock.Step.mean": { "value": 1979987.0, "min": 59944.0, "max": 1979987.0, "count": 33 }, "PushBlock.Step.sum": { "value": 1979987.0, "min": 59944.0, "max": 1979987.0, "count": 33 }, "PushBlock.Policy.ExtrinsicValueEstimate.mean": { "value": 3.8008649349212646, "min": 0.05942888930439949, "max": 3.9855449199676514, "count": 33 }, "PushBlock.Policy.ExtrinsicValueEstimate.sum": { "value": 7784.17138671875, "min": 56.695159912109375, "max": 8676.53125, "count": 33 }, "PushBlock.Environment.CumulativeReward.mean": { "value": 4.902757207516929, "min": 0.5308590738780119, "max": 4.942098505536983, "count": 33 }, "PushBlock.Environment.CumulativeReward.sum": { "value": 8535.700298286974, "min": 23.357799250632524, "max": 9530.296687968075, "count": 33 }, "PushBlock.Policy.ExtrinsicReward.mean": { "value": 4.902757207516929, "min": 0.5308590738780119, "max": 4.942098505536983, "count": 33 }, "PushBlock.Policy.ExtrinsicReward.sum": { "value": 8535.700298286974, "min": 23.357799250632524, "max": 9530.296687968075, "count": 33 }, "PushBlock.Losses.PolicyLoss.mean": { "value": 0.01667110461442332, "min": 0.014226089290546615, "max": 0.02022807457987433, "count": 33 }, "PushBlock.Losses.PolicyLoss.sum": { "value": 0.46679092920385296, "min": 0.4125565894258518, "max": 0.5866141628163556, "count": 33 }, "PushBlock.Losses.ValueLoss.mean": { "value": 0.24411152844272907, "min": 0.044421624923685434, "max": 0.42068228356185416, "count": 33 }, "PushBlock.Losses.ValueLoss.sum": { "value": 6.835122796396414, "min": 1.0661189981684505, "max": 11.846272406478722, "count": 33 }, "PushBlock.Policy.LearningRate.mean": { "value": 7.494681430376785e-06, "min": 7.494681430376785e-06, "max": 0.00029529772031742705, "count": 33 }, "PushBlock.Policy.LearningRate.sum": { "value": 0.00020985108005054998, "min": 0.00020985108005054998, "max": 0.008049111966962747, "count": 33 }, "PushBlock.Policy.Epsilon.mean": { "value": 0.10249819464285714, "min": 0.10249819464285714, "max": 0.19843257291666663, "count": 33 }, "PushBlock.Policy.Epsilon.sum": { "value": 2.86994945, "min": 2.86994945, "max": 5.58303725, "count": 33 }, "PushBlock.Policy.Beta.mean": { "value": 0.0002595696448214286, "min": 0.0002595696448214286, "max": 0.009843414034375001, "count": 33 }, "PushBlock.Policy.Beta.sum": { "value": 0.007267950055000001, "min": 0.007267950055000001, "max": 0.268325421275, "count": 33 }, "PushBlock.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "PushBlock.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1659869658", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1659871453" }, "total": 1794.9030301530001, "count": 1, "self": 0.3835086770000089, "children": { "run_training.setup": { "total": 0.05140996399995856, "count": 1, "self": 0.05140996399995856 }, "TrainerController.start_learning": { "total": 1794.4681115120002, "count": 1, "self": 2.030739208990326, "children": { "TrainerController._reset_env": { "total": 9.773006445000078, "count": 1, "self": 9.773006445000078 }, "TrainerController.advance": { "total": 1782.60274390701, "count": 89722, "self": 2.110499358087054, "children": { "env_step": { "total": 1199.5447667459803, "count": 89722, "self": 1103.1083807310104, "children": { "SubprocessEnvManager._take_step": { "total": 95.46156858598783, "count": 89722, "self": 5.160344101981423, "children": { "TorchPolicy.evaluate": { "total": 90.30122448400641, "count": 62519, "self": 30.280955941039906, "children": { "TorchPolicy.sample_actions": { "total": 60.020268542966505, "count": 62519, "self": 60.020268542966505 } } } } }, "workers": { "total": 0.9748174289820781, "count": 89722, "self": 0.0, "children": { "worker_root": { "total": 1790.3039862030225, "count": 89722, "is_parallel": true, "self": 832.3902925840357, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010899404000042523, "count": 1, "is_parallel": true, "self": 0.00452843700008998, "children": { "_process_rank_one_or_two_observation": { "total": 0.006370966999952543, "count": 4, "is_parallel": true, "self": 0.006370966999952543 } } }, "UnityEnvironment.step": { "total": 0.036228042999937315, "count": 1, "is_parallel": true, "self": 0.0007522309999785648, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007164979999743082, "count": 1, "is_parallel": true, "self": 0.0007164979999743082 }, "communicator.exchange": { "total": 0.03239290599992728, "count": 1, "is_parallel": true, "self": 0.03239290599992728 }, "steps_from_proto": { "total": 0.002366408000057163, "count": 1, "is_parallel": true, "self": 0.00041603300007864163, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019503749999785214, "count": 4, "is_parallel": true, "self": 0.0019503749999785214 } } } } } } }, "UnityEnvironment.step": { "total": 957.9136936189868, "count": 89721, "is_parallel": true, "self": 44.8937281159491, "children": { "UnityEnvironment._generate_step_input": { "total": 41.76090327304382, "count": 89721, "is_parallel": true, "self": 41.76090327304382 }, "communicator.exchange": { "total": 735.1320485239642, "count": 89721, "is_parallel": true, "self": 735.1320485239642 }, "steps_from_proto": { "total": 136.12701370602974, "count": 89721, "is_parallel": true, "self": 28.151503282091085, "children": { "_process_rank_one_or_two_observation": { "total": 107.97551042393866, "count": 358884, "is_parallel": true, "self": 107.97551042393866 } } } } } } } } } } }, "trainer_advance": { "total": 580.9474778029428, "count": 89722, "self": 3.7922236129238627, "children": { "process_trajectory": { "total": 227.59626702102332, "count": 89722, "self": 227.33247702502354, "children": { "RLTrainer._checkpoint": { "total": 0.2637899959997867, "count": 4, "self": 0.2637899959997867 } } }, "_update_policy": { "total": 349.5589871689956, "count": 957, "self": 295.4803823849977, "children": { "TorchPPOOptimizer.update": { "total": 54.07860478399789, "count": 5757, "self": 54.07860478399789 } } } } } } }, "trainer_threads": { "total": 1.2810000953322742e-06, "count": 1, "self": 1.2810000953322742e-06 }, "TrainerController._save_models": { "total": 0.06162066999968374, "count": 1, "self": 0.0007391969998025161, "children": { "RLTrainer._checkpoint": { "total": 0.060881472999881225, "count": 1, "self": 0.060881472999881225 } } } } } } }