{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.48494020104408264, "min": 0.4389359652996063, "max": 2.8448941707611084, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4992.9443359375, "min": 4197.14599609375, "max": 29040.6796875, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.192525863647461, "min": 0.47541970014572144, "max": 14.546624183654785, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2909.4677734375, "min": 92.2314224243164, "max": 2976.600341796875, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.066127688083889, "min": 0.05954793449857379, "max": 0.0798550780768981, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.330638440419445, "min": 0.23819173799429516, "max": 0.3798116480408912, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1481990499239342, "min": 0.12890622285651226, "max": 0.3219272695189598, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.740995249619671, "min": 0.5160722804127955, "max": 1.5637007294332281, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000039e-07, "min": 7.032997656000039e-07, "max": 0.00029918820027059994, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000196e-06, "min": 3.5164988280000196e-06, "max": 0.0014885160038279998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.1997294, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.4029176, "max": 0.996172, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000067e-05, "min": 2.1696560000000067e-05, "max": 0.004986497059999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000034, "min": 0.00010848280000000034, "max": 0.024808982800000004, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.363636363636363, "min": 4.068181818181818, "max": 28.545454545454547, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1560.0, "min": 179.0, "max": 1563.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.363636363636363, "min": 4.068181818181818, "max": 28.545454545454547, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1560.0, "min": 179.0, "max": 1563.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1754699136", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --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": "1754705193" }, "total": 6057.009083854, "count": 1, "self": 1.0899876410003344, "children": { "run_training.setup": { "total": 0.04210754299992914, "count": 1, "self": 0.04210754299992914 }, "TrainerController.start_learning": { "total": 6055.876988669999, "count": 1, "self": 6.029749486847322, "children": { "TrainerController._reset_env": { "total": 2.068806665000011, "count": 1, "self": 2.068806665000011 }, "TrainerController.advance": { "total": 6047.651694401154, "count": 181864, "self": 6.389894466591613, "children": { "env_step": { "total": 4226.218375478724, "count": 181864, "self": 3669.7648168563333, "children": { "SubprocessEnvManager._take_step": { "total": 552.4364153810843, "count": 181864, "self": 18.211977415011006, "children": { "TorchPolicy.evaluate": { "total": 534.2244379660733, "count": 181864, "self": 534.2244379660733 } } }, "workers": { "total": 4.0171432413062576, "count": 181864, "self": 0.0, "children": { "worker_root": { "total": 6037.240575935578, "count": 181864, "is_parallel": true, "self": 2824.0741641150885, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002369099000134156, "count": 1, "is_parallel": true, "self": 0.000705273999756173, "children": { "_process_rank_one_or_two_observation": { "total": 0.001663825000377983, "count": 10, "is_parallel": true, "self": 0.001663825000377983 } } }, "UnityEnvironment.step": { "total": 0.04726861500012092, "count": 1, "is_parallel": true, "self": 0.0007977440004651726, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005030379998061107, "count": 1, "is_parallel": true, "self": 0.0005030379998061107 }, "communicator.exchange": { "total": 0.04348146599977554, "count": 1, "is_parallel": true, "self": 0.04348146599977554 }, "steps_from_proto": { "total": 0.0024863670000740967, "count": 1, "is_parallel": true, "self": 0.0005072769999969751, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019790900000771217, "count": 10, "is_parallel": true, "self": 0.0019790900000771217 } } } } } } }, "UnityEnvironment.step": { "total": 3213.1664118204894, "count": 181863, "is_parallel": true, "self": 150.78712598213588, "children": { "UnityEnvironment._generate_step_input": { "total": 78.341402653356, "count": 181863, "is_parallel": true, "self": 78.341402653356 }, "communicator.exchange": { "total": 2537.1597086211486, "count": 181863, "is_parallel": true, "self": 2537.1597086211486 }, "steps_from_proto": { "total": 446.8781745638489, "count": 181863, "is_parallel": true, "self": 84.53929674381061, "children": { "_process_rank_one_or_two_observation": { "total": 362.3388778200383, "count": 1818630, "is_parallel": true, "self": 362.3388778200383 } } } } } } } } } } }, "trainer_advance": { "total": 1815.0434244558382, "count": 181864, "self": 8.097857849059437, "children": { "process_trajectory": { "total": 309.69932153977925, "count": 181864, "self": 306.21368697577645, "children": { "RLTrainer._checkpoint": { "total": 3.485634564002794, "count": 40, "self": 3.485634564002794 } } }, "_update_policy": { "total": 1497.2462450669996, "count": 909, "self": 566.3734445209602, "children": { "TorchPPOOptimizer.update": { "total": 930.8728005460393, "count": 46356, "self": 930.8728005460393 } } } } } } }, "trainer_threads": { "total": 1.710999640636146e-06, "count": 1, "self": 1.710999640636146e-06 }, "TrainerController._save_models": { "total": 0.12673640599859937, "count": 1, "self": 0.0030466929983958835, "children": { "RLTrainer._checkpoint": { "total": 0.12368971300020348, "count": 1, "self": 0.12368971300020348 } } } } } } }