{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.873246431350708, "min": 0.873246431350708, "max": 2.8476200103759766, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8299.333984375, "min": 8299.333984375, "max": 29068.50390625, "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": 13.297614097595215, "min": 0.45628392696380615, "max": 13.297614097595215, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2593.03466796875, "min": 88.51908111572266, "max": 2707.156005859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06851533102482843, "min": 0.06212644144959674, "max": 0.07566496072845172, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2740613240993137, "min": 0.24850576579838696, "max": 0.36116081155470214, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21863616274341063, "min": 0.18955542539119694, "max": 0.3321287851561518, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8745446509736425, "min": 0.7582217015647877, "max": 1.660643925780759, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.0013851600382800001, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "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": 25.954545454545453, "min": 4.181818181818182, "max": 26.054545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1142.0, "min": 184.0, "max": 1433.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.954545454545453, "min": 4.181818181818182, "max": 26.054545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1142.0, "min": 184.0, "max": 1433.0, "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": "1750690562", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750691047" }, "total": 485.144688643, "count": 1, "self": 0.44162469200000487, "children": { "run_training.setup": { "total": 0.024846223999986705, "count": 1, "self": 0.024846223999986705 }, "TrainerController.start_learning": { "total": 484.678217727, "count": 1, "self": 0.3829240630047934, "children": { "TrainerController._reset_env": { "total": 3.3238361820000364, "count": 1, "self": 3.3238361820000364 }, "TrainerController.advance": { "total": 480.8851140439952, "count": 18192, "self": 0.4146370399946022, "children": { "env_step": { "total": 323.8248205329972, "count": 18192, "self": 249.271150477993, "children": { "SubprocessEnvManager._take_step": { "total": 74.31599836999897, "count": 18192, "self": 1.3349064690103774, "children": { "TorchPolicy.evaluate": { "total": 72.98109190098859, "count": 18192, "self": 72.98109190098859 } } }, "workers": { "total": 0.23767168500523894, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 483.1032995500087, "count": 18192, "is_parallel": true, "self": 264.0924654860134, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005443952000007357, "count": 1, "is_parallel": true, "self": 0.0038714570000593085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015724949999480486, "count": 10, "is_parallel": true, "self": 0.0015724949999480486 } } }, "UnityEnvironment.step": { "total": 0.041589897999983805, "count": 1, "is_parallel": true, "self": 0.0005945059999135083, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041408200002024387, "count": 1, "is_parallel": true, "self": 0.00041408200002024387 }, "communicator.exchange": { "total": 0.03873012000002518, "count": 1, "is_parallel": true, "self": 0.03873012000002518 }, "steps_from_proto": { "total": 0.0018511900000248716, "count": 1, "is_parallel": true, "self": 0.0003315609999958724, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015196290000289991, "count": 10, "is_parallel": true, "self": 0.0015196290000289991 } } } } } } }, "UnityEnvironment.step": { "total": 219.01083406399533, "count": 18191, "is_parallel": true, "self": 10.256811875992014, "children": { "UnityEnvironment._generate_step_input": { "total": 5.814517222996528, "count": 18191, "is_parallel": true, "self": 5.814517222996528 }, "communicator.exchange": { "total": 169.0502204069989, "count": 18191, "is_parallel": true, "self": 169.0502204069989 }, "steps_from_proto": { "total": 33.88928455800789, "count": 18191, "is_parallel": true, "self": 6.0338878399976466, "children": { "_process_rank_one_or_two_observation": { "total": 27.85539671801024, "count": 181910, "is_parallel": true, "self": 27.85539671801024 } } } } } } } } } } }, "trainer_advance": { "total": 156.6456564710034, "count": 18192, "self": 0.4724932060029232, "children": { "process_trajectory": { "total": 28.747298602000342, "count": 18192, "self": 28.276052557000185, "children": { "RLTrainer._checkpoint": { "total": 0.4712460450001572, "count": 4, "self": 0.4712460450001572 } } }, "_update_policy": { "total": 127.42586466300014, "count": 90, "self": 52.51631445199706, "children": { "TorchPPOOptimizer.update": { "total": 74.90955021100308, "count": 6116, "self": 74.90955021100308 } } } } } } }, "trainer_threads": { "total": 1.9809999685094226e-06, "count": 1, "self": 1.9809999685094226e-06 }, "TrainerController._save_models": { "total": 0.08634145700000317, "count": 1, "self": 0.0009775339999578136, "children": { "RLTrainer._checkpoint": { "total": 0.08536392300004536, "count": 1, "self": 0.08536392300004536 } } } } } } }