{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.497833490371704, "min": 1.497833490371704, "max": 2.8853862285614014, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14235.4091796875, "min": 14235.4091796875, "max": 29454.0234375, "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": 8.567286491394043, "min": 0.15067428350448608, "max": 8.572086334228516, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1670.620849609375, "min": 29.230812072753906, "max": 1748.70556640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06495434990810121, "min": 0.061143522478717696, "max": 0.079103218278261, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25981739963240486, "min": 0.25398102507689124, "max": 0.36427939842813467, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24383397882475571, "min": 0.10935764065395823, "max": 0.27314069465387103, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9753359152990229, "min": 0.4374305626158329, "max": 1.3629406068254921, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6940973060000025e-06, "min": 2.6940973060000025e-06, "max": 9.729400270599998e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.077638922400001e-05, "min": 1.077638922400001e-05, "max": 0.0004617200382800001, "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": 16.65909090909091, "min": 2.977272727272727, "max": 17.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 733.0, "min": 131.0, "max": 949.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 16.65909090909091, "min": 2.977272727272727, "max": 17.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 733.0, "min": 131.0, "max": 949.0, "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": "1790942389", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/kaggle/working/mlagents-py310/bin/mlagents-learn /kaggle/working/ml-agents/config/ppo/SnowballTarget.yaml --env=/kaggle/working/ml-agents/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": "1790942794" }, "total": 405.1899806010001, "count": 1, "self": 0.3836439579999933, "children": { "run_training.setup": { "total": 0.02267325000002529, "count": 1, "self": 0.02267325000002529 }, "TrainerController.start_learning": { "total": 404.7836633930001, "count": 1, "self": 0.34798989101363986, "children": { "TrainerController._reset_env": { "total": 3.137995953999962, "count": 1, "self": 3.137995953999962 }, "TrainerController.advance": { "total": 401.2163042149864, "count": 18192, "self": 0.35686066295284036, "children": { "env_step": { "total": 287.24950266501037, "count": 18192, "self": 216.31292143602968, "children": { "SubprocessEnvManager._take_step": { "total": 70.72911648101945, "count": 18192, "self": 1.2538790670109847, "children": { "TorchPolicy.evaluate": { "total": 69.47523741400846, "count": 18192, "self": 69.47523741400846 } } }, "workers": { "total": 0.20746474796123948, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 403.62266546502633, "count": 18192, "is_parallel": true, "self": 212.37659469003893, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019213900000067952, "count": 1, "is_parallel": true, "self": 0.0006003480002618744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013210419997449208, "count": 10, "is_parallel": true, "self": 0.0013210419997449208 } } }, "UnityEnvironment.step": { "total": 0.03922389699982887, "count": 1, "is_parallel": true, "self": 0.0006634069991378055, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002734890003921464, "count": 1, "is_parallel": true, "self": 0.0002734890003921464 }, "communicator.exchange": { "total": 0.03596988200024498, "count": 1, "is_parallel": true, "self": 0.03596988200024498 }, "steps_from_proto": { "total": 0.0023171190000539355, "count": 1, "is_parallel": true, "self": 0.0004252700000506593, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018918490000032762, "count": 10, "is_parallel": true, "self": 0.0018918490000032762 } } } } } } }, "UnityEnvironment.step": { "total": 191.2460707749874, "count": 18191, "is_parallel": true, "self": 8.132566140935978, "children": { "UnityEnvironment._generate_step_input": { "total": 4.475337157057766, "count": 18191, "is_parallel": true, "self": 4.475337157057766 }, "communicator.exchange": { "total": 152.66968001595933, "count": 18191, "is_parallel": true, "self": 152.66968001595933 }, "steps_from_proto": { "total": 25.96848746103433, "count": 18191, "is_parallel": true, "self": 4.624661235050098, "children": { "_process_rank_one_or_two_observation": { "total": 21.34382622598423, "count": 181910, "is_parallel": true, "self": 21.34382622598423 } } } } } } } } } } }, "trainer_advance": { "total": 113.60994088702319, "count": 18192, "self": 0.4069053880202773, "children": { "process_trajectory": { "total": 23.124361202003, "count": 18192, "self": 22.747063627003172, "children": { "RLTrainer._checkpoint": { "total": 0.3772975749998295, "count": 4, "self": 0.3772975749998295 } } }, "_update_policy": { "total": 90.0786742969999, "count": 90, "self": 34.96916285299858, "children": { "TorchPPOOptimizer.update": { "total": 55.10951144400133, "count": 4587, "self": 55.10951144400133 } } } } } } }, "trainer_threads": { "total": 9.800000952964183e-07, "count": 1, "self": 9.800000952964183e-07 }, "TrainerController._save_models": { "total": 0.08137235300000611, "count": 1, "self": 0.0005909999999857973, "children": { "RLTrainer._checkpoint": { "total": 0.08078135300002032, "count": 1, "self": 0.08078135300002032 } } } } } } }