{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7623308897018433, "min": 0.7623308897018433, "max": 2.8241353034973145, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7245.19287109375, "min": 7245.19287109375, "max": 28828.7734375, "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": 12.987959861755371, "min": 0.4588600695133209, "max": 12.987959861755371, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2532.652099609375, "min": 89.01885223388672, "max": 2638.51318359375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06821689921529397, "min": 0.05779405675837588, "max": 0.07647052544166845, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2728675968611759, "min": 0.2605248839073979, "max": 0.36649335032887076, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1981534477250249, "min": 0.14688582637452285, "max": 0.27134921701223247, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7926137909000996, "min": 0.5875433054980914, "max": 1.2795328570931563, "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": 25.363636363636363, "min": 3.9545454545454546, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 174.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.9545454545454546, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 174.0, "max": 1401.0, "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": "1782532261", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "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": "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": "1782532725" }, "total": 463.3359227399999, "count": 1, "self": 0.43230175699977735, "children": { "run_training.setup": { "total": 0.022697643000128664, "count": 1, "self": 0.022697643000128664 }, "TrainerController.start_learning": { "total": 462.88092334, "count": 1, "self": 0.3750114979955015, "children": { "TrainerController._reset_env": { "total": 2.841866939000056, "count": 1, "self": 2.841866939000056 }, "TrainerController.advance": { "total": 459.5706084850044, "count": 18192, "self": 0.38856157402892677, "children": { "env_step": { "total": 338.81981900297956, "count": 18192, "self": 264.9808331169713, "children": { "SubprocessEnvManager._take_step": { "total": 73.60512077700218, "count": 18192, "self": 1.3258972349992746, "children": { "TorchPolicy.evaluate": { "total": 72.27922354200291, "count": 18192, "self": 72.27922354200291 } } }, "workers": { "total": 0.23386510900604662, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 461.15691525701914, "count": 18192, "is_parallel": true, "self": 228.27663914605068, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005286625000053391, "count": 1, "is_parallel": true, "self": 0.0037166470001466223, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015699779999067687, "count": 10, "is_parallel": true, "self": 0.0015699779999067687 } } }, "UnityEnvironment.step": { "total": 0.03857087899996259, "count": 1, "is_parallel": true, "self": 0.0007128580000426155, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004263240000454971, "count": 1, "is_parallel": true, "self": 0.0004263240000454971 }, "communicator.exchange": { "total": 0.03524529299988899, "count": 1, "is_parallel": true, "self": 0.03524529299988899 }, "steps_from_proto": { "total": 0.0021864039999854867, "count": 1, "is_parallel": true, "self": 0.0004369379998934164, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017494660000920703, "count": 10, "is_parallel": true, "self": 0.0017494660000920703 } } } } } } }, "UnityEnvironment.step": { "total": 232.88027611096845, "count": 18191, "is_parallel": true, "self": 10.606029249971016, "children": { "UnityEnvironment._generate_step_input": { "total": 5.790739017007581, "count": 18191, "is_parallel": true, "self": 5.790739017007581 }, "communicator.exchange": { "total": 177.12682645698396, "count": 18191, "is_parallel": true, "self": 177.12682645698396 }, "steps_from_proto": { "total": 39.35668138700589, "count": 18191, "is_parallel": true, "self": 6.881687290996297, "children": { "_process_rank_one_or_two_observation": { "total": 32.474994096009596, "count": 181910, "is_parallel": true, "self": 32.474994096009596 } } } } } } } } } } }, "trainer_advance": { "total": 120.36222790799593, "count": 18192, "self": 0.459893963012064, "children": { "process_trajectory": { "total": 24.595513192984527, "count": 18192, "self": 24.210270772984586, "children": { "RLTrainer._checkpoint": { "total": 0.38524241999994047, "count": 4, "self": 0.38524241999994047 } } }, "_update_policy": { "total": 95.30682075199934, "count": 90, "self": 38.62820900100269, "children": { "TorchPPOOptimizer.update": { "total": 56.67861175099665, "count": 4587, "self": 56.67861175099665 } } } } } } }, "trainer_threads": { "total": 9.380000847158954e-07, "count": 1, "self": 9.380000847158954e-07 }, "TrainerController._save_models": { "total": 0.09343547999992552, "count": 1, "self": 0.0007601069999054744, "children": { "RLTrainer._checkpoint": { "total": 0.09267537300002004, "count": 1, "self": 0.09267537300002004 } } } } } } }