{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9023484587669373, "min": 0.9023484587669373, "max": 2.8539953231811523, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9211.1728515625, "min": 8872.3330078125, "max": 29133.583984375, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.001004219055176, "min": 0.3834740221500397, "max": 14.001004219055176, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2730.19580078125, "min": 74.39395904541016, "max": 2869.69140625, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07089135536257613, "min": 0.06464388629517945, "max": 0.07333509435923, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2835654214503045, "min": 0.2585755451807178, "max": 0.35084965729243667, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16454049280899413, "min": 0.1343507562589366, "max": 0.2542190472694005, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6581619712359765, "min": 0.5374030250357464, "max": 1.2710952363470023, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.891098702999994e-06, "min": 3.891098702999994e-06, "max": 0.000295941001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5564394811999976e-05, "min": 1.5564394811999976e-05, "max": 0.0014425800191399996, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1006485, "min": 0.1006485, "max": 0.1493235, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.402594, "min": 0.402594, "max": 0.7404299999999999, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.472029999999992e-05, "min": 7.472029999999992e-05, "max": 0.004932485300000001, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00029888119999999966, "min": 0.00029888119999999966, "max": 0.024044914, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.227272727272727, "min": 4.113636363636363, "max": 27.75, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1198.0, "min": 181.0, "max": 1515.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.227272727272727, "min": 4.113636363636363, "max": 27.75, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1198.0, "min": 181.0, "max": 1515.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740054201", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740055633" }, "total": 1431.5879311209999, "count": 1, "self": 0.6502888630000143, "children": { "run_training.setup": { "total": 0.02428176299997631, "count": 1, "self": 0.02428176299997631 }, "TrainerController.start_learning": { "total": 1430.913360495, "count": 1, "self": 0.8706237939989023, "children": { "TrainerController._reset_env": { "total": 3.18358776499997, "count": 1, "self": 3.18358776499997 }, "TrainerController.advance": { "total": 1426.6804487890008, "count": 36392, "self": 0.8882673829609757, "children": { "env_step": { "total": 674.6170187010016, "count": 36392, "self": 510.84276993699996, "children": { "SubprocessEnvManager._take_step": { "total": 163.26102320401617, "count": 36392, "self": 2.834803801015653, "children": { "TorchPolicy.evaluate": { "total": 160.42621940300052, "count": 36392, "self": 160.42621940300052 } } }, "workers": { "total": 0.5132255599854716, "count": 36392, "self": 0.0, "children": { "worker_root": { "total": 1427.8470249079946, "count": 36392, "is_parallel": true, "self": 981.1885582130028, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006615025999963109, "count": 1, "is_parallel": true, "self": 0.004971377999822835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016436480001402742, "count": 10, "is_parallel": true, "self": 0.0016436480001402742 } } }, "UnityEnvironment.step": { "total": 0.036550810999983696, "count": 1, "is_parallel": true, "self": 0.0006456569999500061, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040384200002563375, "count": 1, "is_parallel": true, "self": 0.00040384200002563375 }, "communicator.exchange": { "total": 0.0334315509999783, "count": 1, "is_parallel": true, "self": 0.0334315509999783 }, "steps_from_proto": { "total": 0.0020697610000297573, "count": 1, "is_parallel": true, "self": 0.0003847999999493368, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016849610000804205, "count": 10, "is_parallel": true, "self": 0.0016849610000804205 } } } } } } }, "UnityEnvironment.step": { "total": 446.6584666949918, "count": 36391, "is_parallel": true, "self": 20.852096322992566, "children": { "UnityEnvironment._generate_step_input": { "total": 11.864212770987649, "count": 36391, "is_parallel": true, "self": 11.864212770987649 }, "communicator.exchange": { "total": 344.9667134539927, "count": 36391, "is_parallel": true, "self": 344.9667134539927 }, "steps_from_proto": { "total": 68.97544414701883, "count": 36391, "is_parallel": true, "self": 12.621320723042686, "children": { "_process_rank_one_or_two_observation": { "total": 56.35412342397615, "count": 363910, "is_parallel": true, "self": 56.35412342397615 } } } } } } } } } } }, "trainer_advance": { "total": 751.1751627050382, "count": 36392, "self": 1.0460782780110094, "children": { "process_trajectory": { "total": 60.422620794026045, "count": 36392, "self": 59.33849674002596, "children": { "RLTrainer._checkpoint": { "total": 1.0841240540000854, "count": 8, "self": 1.0841240540000854 } } }, "_update_policy": { "total": 689.7064636330011, "count": 181, "self": 261.94226836599614, "children": { "TorchPPOOptimizer.update": { "total": 427.764195267005, "count": 30760, "self": 427.764195267005 } } } } } } }, "trainer_threads": { "total": 1.134000058300444e-06, "count": 1, "self": 1.134000058300444e-06 }, "TrainerController._save_models": { "total": 0.17869901300014135, "count": 1, "self": 0.0034200310001324397, "children": { "RLTrainer._checkpoint": { "total": 0.1752789820000089, "count": 1, "self": 0.1752789820000089 } } } } } } }