{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7089861035346985, "min": 0.6878647208213806, "max": 2.8224806785583496, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6738.2041015625, "min": 6738.2041015625, "max": 28811.8828125, "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": 11.892724990844727, "min": 0.41852128505706787, "max": 11.892724990844727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2319.081298828125, "min": 81.19313049316406, "max": 2404.543212890625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07258445174403616, "min": 0.05973032061895127, "max": 0.07415446201875789, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29033780697614464, "min": 0.2666096086065997, "max": 0.3707723100937894, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18749241698898522, "min": 0.15183293286656194, "max": 0.284510766174279, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7499696679559409, "min": 0.6073317314662477, "max": 1.422553830871395, "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": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "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": 23.90909090909091, "min": 3.6818181818181817, "max": 23.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1052.0, "min": 162.0, "max": 1281.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.90909090909091, "min": 3.6818181818181817, "max": 23.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1052.0, "min": 162.0, "max": 1281.0, "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": "1785417466", "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=/content/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785417940" }, "total": 473.1342420000001, "count": 1, "self": 0.4785402890001933, "children": { "run_training.setup": { "total": 0.03011202899995169, "count": 1, "self": 0.03011202899995169 }, "TrainerController.start_learning": { "total": 472.62558968199994, "count": 1, "self": 0.4056838880143232, "children": { "TrainerController._reset_env": { "total": 3.196018864999928, "count": 1, "self": 3.196018864999928 }, "TrainerController.advance": { "total": 468.9422371989857, "count": 18192, "self": 0.40434145797200927, "children": { "env_step": { "total": 346.9847663669965, "count": 18192, "self": 271.9671130299969, "children": { "SubprocessEnvManager._take_step": { "total": 74.78096171999721, "count": 18192, "self": 1.3446824490000608, "children": { "TorchPolicy.evaluate": { "total": 73.43627927099715, "count": 18192, "self": 73.43627927099715 } } }, "workers": { "total": 0.23669161700240693, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 470.6234718239758, "count": 18192, "is_parallel": true, "self": 231.92978922399584, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0050070930000174485, "count": 1, "is_parallel": true, "self": 0.003618052999968313, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013890400000491354, "count": 10, "is_parallel": true, "self": 0.0013890400000491354 } } }, "UnityEnvironment.step": { "total": 0.04053635100001429, "count": 1, "is_parallel": true, "self": 0.0005788060000213591, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004466600000796461, "count": 1, "is_parallel": true, "self": 0.0004466600000796461 }, "communicator.exchange": { "total": 0.03748977099996864, "count": 1, "is_parallel": true, "self": 0.03748977099996864 }, "steps_from_proto": { "total": 0.002021113999944646, "count": 1, "is_parallel": true, "self": 0.0003827689998843198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016383450000603261, "count": 10, "is_parallel": true, "self": 0.0016383450000603261 } } } } } } }, "UnityEnvironment.step": { "total": 238.69368259997998, "count": 18191, "is_parallel": true, "self": 11.037339355976428, "children": { "UnityEnvironment._generate_step_input": { "total": 5.810042849012234, "count": 18191, "is_parallel": true, "self": 5.810042849012234 }, "communicator.exchange": { "total": 182.5958491180013, "count": 18191, "is_parallel": true, "self": 182.5958491180013 }, "steps_from_proto": { "total": 39.25045127699002, "count": 18191, "is_parallel": true, "self": 6.970783648997212, "children": { "_process_rank_one_or_two_observation": { "total": 32.27966762799281, "count": 181910, "is_parallel": true, "self": 32.27966762799281 } } } } } } } } } } }, "trainer_advance": { "total": 121.5531293740172, "count": 18192, "self": 0.5066943690229664, "children": { "process_trajectory": { "total": 25.336120383994285, "count": 18192, "self": 24.877627061994417, "children": { "RLTrainer._checkpoint": { "total": 0.4584933219998675, "count": 4, "self": 0.4584933219998675 } } }, "_update_policy": { "total": 95.71031462099995, "count": 90, "self": 38.42834517700419, "children": { "TorchPPOOptimizer.update": { "total": 57.28196944399576, "count": 4587, "self": 57.28196944399576 } } } } } } }, "trainer_threads": { "total": 1.3799999578623101e-06, "count": 1, "self": 1.3799999578623101e-06 }, "TrainerController._save_models": { "total": 0.08164835000002313, "count": 1, "self": 0.0007866930000091088, "children": { "RLTrainer._checkpoint": { "total": 0.08086165700001402, "count": 1, "self": 0.08086165700001402 } } } } } } }