{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.8172171115875244, "min": 2.8163089752197266, "max": 2.89035701751709, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 25628.224609375, "min": 25031.353515625, "max": 32080.0703125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199800.0, "min": 9800.0, "max": 199800.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199800.0, "min": 9800.0, "max": 199800.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8233018517494202, "min": -0.011939087882637978, "max": 0.8323451280593872, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 41.16509246826172, "min": -0.5850152969360352, "max": 41.61725616455078, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 5.62, "min": 2.32, "max": 6.72, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 281.0, "min": 116.0, "max": 336.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.62, "min": 2.32, "max": 6.72, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 281.0, "min": 116.0, "max": 336.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.036180816042032764, "min": 0.033134592222849694, "max": 0.03790047818227965, "count": 3 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.036180816042032764, "min": 0.033134592222849694, "max": 0.03790047818227965, "count": 3 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1797575865473066, "min": 0.09191623086832007, "max": 0.1797575865473066, "count": 3 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.1797575865473066, "min": 0.09191623086832007, "max": 0.1797575865473066, "count": 3 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 4.820007590000001e-05, "min": 4.820007590000001e-05, "max": 0.00014940002529999997, "count": 3 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.820007590000001e-05, "min": 4.820007590000001e-05, "max": 0.00014940002529999997, "count": 3 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12409999999999999, "min": 0.12409999999999999, "max": 0.17470000000000005, "count": 3 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.12409999999999999, "min": 0.12409999999999999, "max": 0.17470000000000005, "count": 3 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0012125900000000002, "min": 0.0012125900000000002, "max": 0.0037375299999999993, "count": 3 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0012125900000000002, "min": 0.0012125900000000002, "max": 0.0037375299999999993, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678966750", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1678967221" }, "total": 470.9644596820001, "count": 1, "self": 0.7393210360002058, "children": { "run_training.setup": { "total": 0.1683218629999601, "count": 1, "self": 0.1683218629999601 }, "TrainerController.start_learning": { "total": 470.05681678299993, "count": 1, "self": 0.6051398380063802, "children": { "TrainerController._reset_env": { "total": 9.688412004000043, "count": 1, "self": 9.688412004000043 }, "TrainerController.advance": { "total": 459.52795411599357, "count": 18253, "self": 0.3110773769868729, "children": { "env_step": { "total": 459.2168767390067, "count": 18253, "self": 342.52426972501155, "children": { "SubprocessEnvManager._take_step": { "total": 116.39011052698356, "count": 18253, "self": 2.78399881998007, "children": { "TorchPolicy.evaluate": { "total": 113.60611170700349, "count": 18253, "self": 113.60611170700349 } } }, "workers": { "total": 0.30249648701158094, "count": 18253, "self": 0.0, "children": { "worker_root": { "total": 468.2306526940122, "count": 18253, "is_parallel": true, "self": 213.52482466602112, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006486032999987401, "count": 1, "is_parallel": true, "self": 0.004110517999720287, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023755150002671144, "count": 10, "is_parallel": true, "self": 0.0023755150002671144 } } }, "UnityEnvironment.step": { "total": 0.035253506000003654, "count": 1, "is_parallel": true, "self": 0.0005920839998907468, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004175100000338716, "count": 1, "is_parallel": true, "self": 0.0004175100000338716 }, "communicator.exchange": { "total": 0.03225290199998199, "count": 1, "is_parallel": true, "self": 0.03225290199998199 }, "steps_from_proto": { "total": 0.0019910100000970488, "count": 1, "is_parallel": true, "self": 0.00041303599994080287, "children": { "_process_rank_one_or_two_observation": { "total": 0.001577974000156246, "count": 10, "is_parallel": true, "self": 0.001577974000156246 } } } } } } }, "UnityEnvironment.step": { "total": 254.70582802799106, "count": 18252, "is_parallel": true, "self": 10.001079071025742, "children": { "UnityEnvironment._generate_step_input": { "total": 5.497328919984284, "count": 18252, "is_parallel": true, "self": 5.497328919984284 }, "communicator.exchange": { "total": 205.8407755099854, "count": 18252, "is_parallel": true, "self": 205.8407755099854 }, "steps_from_proto": { "total": 33.36664452699563, "count": 18252, "is_parallel": true, "self": 6.786818986967319, "children": { "_process_rank_one_or_two_observation": { "total": 26.57982554002831, "count": 182520, "is_parallel": true, "self": 26.57982554002831 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003105260000211274, "count": 1, "self": 0.0003105260000211274, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 453.54266026001346, "count": 674462, "is_parallel": true, "self": 16.462227837954515, "children": { "process_trajectory": { "total": 362.5475766100591, "count": 674462, "is_parallel": true, "self": 355.1636938630595, "children": { "RLTrainer._checkpoint": { "total": 7.383882746999575, "count": 20, "is_parallel": true, "self": 7.383882746999575 } } }, "_update_policy": { "total": 74.53285581199987, "count": 3, "is_parallel": true, "self": 51.589059307000866, "children": { "TorchPPOOptimizer.update": { "total": 22.943796504999, "count": 882, "is_parallel": true, "self": 22.943796504999 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23500029899992114, "count": 1, "self": 0.0014614789999995992, "children": { "RLTrainer._checkpoint": { "total": 0.23353881999992154, "count": 1, "self": 0.23353881999992154 } } } } } } }