{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9031887054443359, "min": 0.9031887054443359, "max": 2.8590750694274902, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8583.9052734375, "min": 8583.9052734375, "max": 29185.4375, "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": 13.166674613952637, "min": 0.3928956091403961, "max": 13.166674613952637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2567.50146484375, "min": 76.22174835205078, "max": 2676.31103515625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09569877330253733, "min": 0.08887950444556075, "max": 0.10366391130242561, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3827950932101493, "min": 0.355518017782243, "max": 0.518319556512128, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18674553203962596, "min": 0.11767296464250501, "max": 0.2861367350845945, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7469821281585038, "min": 0.47069185857002005, "max": 1.2938210438279545, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.347009730600001e-05, "min": 1.347009730600001e-05, "max": 0.000486470002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.388038922400004e-05, "min": 5.388038922400004e-05, "max": 0.00230860003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "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.Environment.CumulativeReward.mean": { "value": 25.90909090909091, "min": 3.522727272727273, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 155.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 3.522727272727273, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 155.0, "max": 1406.0, "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": "1754259076", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754259537" }, "total": 460.95096753100006, "count": 1, "self": 0.43818298700023206, "children": { "run_training.setup": { "total": 0.023992966999912824, "count": 1, "self": 0.023992966999912824 }, "TrainerController.start_learning": { "total": 460.4887915769999, "count": 1, "self": 0.31859520101954786, "children": { "TrainerController._reset_env": { "total": 3.277302428999974, "count": 1, "self": 3.277302428999974 }, "TrainerController.advance": { "total": 456.82494497498055, "count": 18192, "self": 0.3567859279650065, "children": { "env_step": { "total": 288.6358884390055, "count": 18192, "self": 222.336950681002, "children": { "SubprocessEnvManager._take_step": { "total": 66.10090989100058, "count": 18192, "self": 1.202463473007242, "children": { "TorchPolicy.evaluate": { "total": 64.89844641799334, "count": 18192, "self": 64.89844641799334 } } }, "workers": { "total": 0.19802786700290653, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 459.1650945160105, "count": 18192, "is_parallel": true, "self": 264.0027181160068, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051515799999606315, "count": 1, "is_parallel": true, "self": 0.003794029000118826, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013575509998418056, "count": 10, "is_parallel": true, "self": 0.0013575509998418056 } } }, "UnityEnvironment.step": { "total": 0.03405810799995379, "count": 1, "is_parallel": true, "self": 0.0005775109999603956, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041098400004102587, "count": 1, "is_parallel": true, "self": 0.00041098400004102587 }, "communicator.exchange": { "total": 0.03133241599994108, "count": 1, "is_parallel": true, "self": 0.03133241599994108 }, "steps_from_proto": { "total": 0.0017371970000112924, "count": 1, "is_parallel": true, "self": 0.00034701200002018595, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013901849999911065, "count": 10, "is_parallel": true, "self": 0.0013901849999911065 } } } } } } }, "UnityEnvironment.step": { "total": 195.16237640000372, "count": 18191, "is_parallel": true, "self": 9.847915562981825, "children": { "UnityEnvironment._generate_step_input": { "total": 5.3740739060176566, "count": 18191, "is_parallel": true, "self": 5.3740739060176566 }, "communicator.exchange": { "total": 149.45328672500023, "count": 18191, "is_parallel": true, "self": 149.45328672500023 }, "steps_from_proto": { "total": 30.487100206004015, "count": 18191, "is_parallel": true, "self": 5.42988035103599, "children": { "_process_rank_one_or_two_observation": { "total": 25.057219854968025, "count": 181910, "is_parallel": true, "self": 25.057219854968025 } } } } } } } } } } }, "trainer_advance": { "total": 167.83227060801005, "count": 18192, "self": 0.3781663880021142, "children": { "process_trajectory": { "total": 26.10834861200783, "count": 18192, "self": 25.75199214700774, "children": { "RLTrainer._checkpoint": { "total": 0.3563564650000899, "count": 4, "self": 0.3563564650000899 } } }, "_update_policy": { "total": 141.3457556080001, "count": 90, "self": 38.90194290801776, "children": { "TorchPPOOptimizer.update": { "total": 102.44381269998235, "count": 9177, "self": 102.44381269998235 } } } } } } }, "trainer_threads": { "total": 8.749998414714355e-07, "count": 1, "self": 8.749998414714355e-07 }, "TrainerController._save_models": { "total": 0.0679480969999986, "count": 1, "self": 0.0005284789999677741, "children": { "RLTrainer._checkpoint": { "total": 0.06741961800003082, "count": 1, "self": 0.06741961800003082 } } } } } } }