{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2504703998565674, "min": 1.2504703998565674, "max": 2.886979579925537, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11980.7568359375, "min": 11980.7568359375, "max": 29819.61328125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.324289321899414, "min": 0.3100736439228058, "max": 11.324289321899414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2208.236328125, "min": 60.15428924560547, "max": 2275.871337890625, "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.Losses.PolicyLoss.mean": { "value": 0.028035664016594335, "min": 0.02413206558958336, "max": 0.040091094425103314, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.11214265606637734, "min": 0.09652826235833344, "max": 0.18003724430309379, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2651437499249975, "min": 0.12131588517998657, "max": 0.3117944523692131, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.06057499969999, "min": 0.48526354071994626, "max": 1.524265892803669, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.0013851600382799997, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102694, "min": 0.102694, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.410776, "min": 0.410776, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 22.113636363636363, "min": 3.2045454545454546, "max": 22.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 973.0, "min": 141.0, "max": 1223.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.113636363636363, "min": 3.2045454545454546, "max": 22.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 973.0, "min": 141.0, "max": 1223.0, "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 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675755925", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1675756360" }, "total": 434.1099380489999, "count": 1, "self": 0.3954991099999461, "children": { "run_training.setup": { "total": 0.1101448749999463, "count": 1, "self": 0.1101448749999463 }, "TrainerController.start_learning": { "total": 433.604294064, "count": 1, "self": 0.5428597679949689, "children": { "TrainerController._reset_env": { "total": 9.327611589000071, "count": 1, "self": 9.327611589000071 }, "TrainerController.advance": { "total": 423.5445697760049, "count": 18219, "self": 0.2891882430045598, "children": { "env_step": { "total": 423.25538153300033, "count": 18219, "self": 282.88468341298744, "children": { "SubprocessEnvManager._take_step": { "total": 140.09745065201434, "count": 18219, "self": 1.4363491220012747, "children": { "TorchPolicy.evaluate": { "total": 138.66110153001307, "count": 18219, "self": 32.61629586801746, "children": { "TorchPolicy.sample_actions": { "total": 106.04480566199561, "count": 18219, "self": 106.04480566199561 } } } } }, "workers": { "total": 0.2732474679985444, "count": 18219, "self": 0.0, "children": { "worker_root": { "total": 432.06418415598864, "count": 18219, "is_parallel": true, "self": 197.0118603989754, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005939262999959283, "count": 1, "is_parallel": true, "self": 0.0034841060003145685, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024551569996447142, "count": 10, "is_parallel": true, "self": 0.0024551569996447142 } } }, "UnityEnvironment.step": { "total": 0.04520259599996734, "count": 1, "is_parallel": true, "self": 0.0004554909999114898, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002964349999956539, "count": 1, "is_parallel": true, "self": 0.0002964349999956539 }, "communicator.exchange": { "total": 0.04300678300000982, "count": 1, "is_parallel": true, "self": 0.04300678300000982 }, "steps_from_proto": { "total": 0.0014438870000503812, "count": 1, "is_parallel": true, "self": 0.0003722930001686109, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010715939998817703, "count": 10, "is_parallel": true, "self": 0.0010715939998817703 } } } } } } }, "UnityEnvironment.step": { "total": 235.05232375701326, "count": 18218, "is_parallel": true, "self": 9.426452641012247, "children": { "UnityEnvironment._generate_step_input": { "total": 5.136579784015794, "count": 18218, "is_parallel": true, "self": 5.136579784015794 }, "communicator.exchange": { "total": 189.85224114298637, "count": 18218, "is_parallel": true, "self": 189.85224114298637 }, "steps_from_proto": { "total": 30.637050188998842, "count": 18218, "is_parallel": true, "self": 6.6889143440049565, "children": { "_process_rank_one_or_two_observation": { "total": 23.948135844993885, "count": 182180, "is_parallel": true, "self": 23.948135844993885 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016127699996104639, "count": 1, "self": 0.00016127699996104639, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 419.55231472893195, "count": 490712, "is_parallel": true, "self": 12.008696559993837, "children": { "process_trajectory": { "total": 301.85984186193787, "count": 490712, "is_parallel": true, "self": 300.4180089849382, "children": { "RLTrainer._checkpoint": { "total": 1.4418328769996833, "count": 4, "is_parallel": true, "self": 1.4418328769996833 } } }, "_update_policy": { "total": 105.68377630700024, "count": 90, "is_parallel": true, "self": 60.384449014998154, "children": { "TorchPPOOptimizer.update": { "total": 45.29932729200209, "count": 1080, "is_parallel": true, "self": 45.29932729200209 } } } } } } } } }, "TrainerController._save_models": { "total": 0.18909165400009442, "count": 1, "self": 0.0011069330000736954, "children": { "RLTrainer._checkpoint": { "total": 0.18798472100002073, "count": 1, "self": 0.18798472100002073 } } } } } } }