{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2647666931152344, "min": 1.2647666931152344, "max": 2.863877534866333, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 13022.0380859375, "min": 12495.392578125, "max": 29234.4609375, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 10.736746788024902, "min": 0.35800108313560486, "max": 10.736746788024902, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2190.29638671875, "min": 69.45220947265625, "max": 2190.29638671875, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07238719422249215, "min": 0.060196596117463086, "max": 0.07477123151058514, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3619359711124608, "min": 0.24078638446985234, "max": 0.3619359711124608, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24836751298577178, "min": 0.0922892786626357, "max": 0.30543570651435387, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2418375649288589, "min": 0.3691571146505428, "max": 1.4984143718200573, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 22.672727272727272, "min": 2.840909090909091, "max": 22.672727272727272, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1247.0, "min": 125.0, "max": 1247.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.672727272727272, "min": 2.840909090909091, "max": 22.672727272727272, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1247.0, "min": 125.0, "max": 1247.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1745423387", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745423595" }, "total": 207.92418968399988, "count": 1, "self": 0.5419117169997207, "children": { "run_training.setup": { "total": 0.022856881000052454, "count": 1, "self": 0.022856881000052454 }, "TrainerController.start_learning": { "total": 207.3594210860001, "count": 1, "self": 0.1660783539844033, "children": { "TrainerController._reset_env": { "total": 3.495977369000002, "count": 1, "self": 3.495977369000002 }, "TrainerController.advance": { "total": 203.61584394401575, "count": 9128, "self": 0.17079442502836173, "children": { "env_step": { "total": 143.59543823099943, "count": 9128, "self": 109.52477209898757, "children": { "SubprocessEnvManager._take_step": { "total": 33.97441867200018, "count": 9128, "self": 0.6137675400059379, "children": { "TorchPolicy.evaluate": { "total": 33.360651131994246, "count": 9128, "self": 33.360651131994246 } } }, "workers": { "total": 0.09624746001168205, "count": 9128, "self": 0.0, "children": { "worker_root": { "total": 206.55996655101035, "count": 9128, "is_parallel": true, "self": 110.437781060004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005887358000109089, "count": 1, "is_parallel": true, "self": 0.00436246399999618, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015248940001129085, "count": 10, "is_parallel": true, "self": 0.0015248940001129085 } } }, "UnityEnvironment.step": { "total": 0.08112759899995581, "count": 1, "is_parallel": true, "self": 0.0005576129999553814, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037815900009263714, "count": 1, "is_parallel": true, "self": 0.00037815900009263714 }, "communicator.exchange": { "total": 0.07419107600003372, "count": 1, "is_parallel": true, "self": 0.07419107600003372 }, "steps_from_proto": { "total": 0.006000750999874072, "count": 1, "is_parallel": true, "self": 0.00037654099924111506, "children": { "_process_rank_one_or_two_observation": { "total": 0.0056242100006329565, "count": 10, "is_parallel": true, "self": 0.0056242100006329565 } } } } } } }, "UnityEnvironment.step": { "total": 96.12218549100635, "count": 9127, "is_parallel": true, "self": 4.68194382100387, "children": { "UnityEnvironment._generate_step_input": { "total": 2.7253682190116706, "count": 9127, "is_parallel": true, "self": 2.7253682190116706 }, "communicator.exchange": { "total": 73.52870396099252, "count": 9127, "is_parallel": true, "self": 73.52870396099252 }, "steps_from_proto": { "total": 15.186169489998292, "count": 9127, "is_parallel": true, "self": 2.670813903988119, "children": { "_process_rank_one_or_two_observation": { "total": 12.515355586010173, "count": 91270, "is_parallel": true, "self": 12.515355586010173 } } } } } } } } } } }, "trainer_advance": { "total": 59.849611287987955, "count": 9128, "self": 0.196823435993565, "children": { "process_trajectory": { "total": 13.426351267993596, "count": 9128, "self": 13.196248684993407, "children": { "RLTrainer._checkpoint": { "total": 0.23010258300018904, "count": 2, "self": 0.23010258300018904 } } }, "_update_policy": { "total": 46.226436584000794, "count": 45, "self": 18.87292744199749, "children": { "TorchPPOOptimizer.update": { "total": 27.353509142003304, "count": 2292, "self": 27.353509142003304 } } } } } } }, "trainer_threads": { "total": 9.170000794256339e-07, "count": 1, "self": 9.170000794256339e-07 }, "TrainerController._save_models": { "total": 0.0815205019998757, "count": 1, "self": 0.0008095869998214766, "children": { "RLTrainer._checkpoint": { "total": 0.08071091500005423, "count": 1, "self": 0.08071091500005423 } } } } } } }