{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.696609616279602, "min": 0.696609616279602, "max": 2.8352744579315186, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6620.57763671875, "min": 6620.57763671875, "max": 28942.48046875, "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": 11.802757263183594, "min": 0.38978490233421326, "max": 11.855842590332031, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2301.53759765625, "min": 75.61827087402344, "max": 2418.591796875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06956119947740351, "min": 0.061706848162929435, "max": 0.07523903495109385, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27824479790961404, "min": 0.24682739265171774, "max": 0.36489404524749547, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1788107183780156, "min": 0.11141497405433078, "max": 0.29012324412663776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7152428735120624, "min": 0.4456598962173231, "max": 1.2203167703221827, "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": 23.181818181818183, "min": 3.3181818181818183, "max": 23.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1020.0, "min": 146.0, "max": 1277.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.181818181818183, "min": 3.3181818181818183, "max": 23.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1020.0, "min": 146.0, "max": 1277.0, "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": "1735285872", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735286248" }, "total": 375.810574006, "count": 1, "self": 0.3213135149999289, "children": { "run_training.setup": { "total": 0.058057357000052434, "count": 1, "self": 0.058057357000052434 }, "TrainerController.start_learning": { "total": 375.43120313400004, "count": 1, "self": 0.32258889801687474, "children": { "TrainerController._reset_env": { "total": 1.9687174969999433, "count": 1, "self": 1.9687174969999433 }, "TrainerController.advance": { "total": 373.05532376598376, "count": 18192, "self": 0.32444219200442603, "children": { "env_step": { "total": 258.80072875697215, "count": 18192, "self": 194.88347049396407, "children": { "SubprocessEnvManager._take_step": { "total": 63.71721979099948, "count": 18192, "self": 1.1796143459782797, "children": { "TorchPolicy.evaluate": { "total": 62.5376054450212, "count": 18192, "self": 62.5376054450212 } } }, "workers": { "total": 0.20003847200860037, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 374.6667297500326, "count": 18192, "is_parallel": true, "self": 202.46280011901626, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002289842000209319, "count": 1, "is_parallel": true, "self": 0.0006804640006521367, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016093779995571822, "count": 10, "is_parallel": true, "self": 0.0016093779995571822 } } }, "UnityEnvironment.step": { "total": 0.02664588499965248, "count": 1, "is_parallel": true, "self": 0.0004511140000431624, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030347499978233827, "count": 1, "is_parallel": true, "self": 0.00030347499978233827 }, "communicator.exchange": { "total": 0.024591572000190354, "count": 1, "is_parallel": true, "self": 0.024591572000190354 }, "steps_from_proto": { "total": 0.001299723999636626, "count": 1, "is_parallel": true, "self": 0.00027273399973637424, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010269899999002519, "count": 10, "is_parallel": true, "self": 0.0010269899999002519 } } } } } } }, "UnityEnvironment.step": { "total": 172.2039296310163, "count": 18191, "is_parallel": true, "self": 6.19685793796134, "children": { "UnityEnvironment._generate_step_input": { "total": 3.2970655469821395, "count": 18191, "is_parallel": true, "self": 3.2970655469821395 }, "communicator.exchange": { "total": 142.24728810504484, "count": 18191, "is_parallel": true, "self": 142.24728810504484 }, "steps_from_proto": { "total": 20.462718041027983, "count": 18191, "is_parallel": true, "self": 4.013908121953591, "children": { "_process_rank_one_or_two_observation": { "total": 16.448809919074392, "count": 181910, "is_parallel": true, "self": 16.448809919074392 } } } } } } } } } } }, "trainer_advance": { "total": 113.93015281700718, "count": 18192, "self": 0.39601577402254406, "children": { "process_trajectory": { "total": 24.926398363982116, "count": 18192, "self": 24.552189101982094, "children": { "RLTrainer._checkpoint": { "total": 0.37420926200002214, "count": 4, "self": 0.37420926200002214 } } }, "_update_policy": { "total": 88.60773867900252, "count": 90, "self": 35.30114400799357, "children": { "TorchPPOOptimizer.update": { "total": 53.30659467100895, "count": 4587, "self": 53.30659467100895 } } } } } } }, "trainer_threads": { "total": 1.0069998097606003e-06, "count": 1, "self": 1.0069998097606003e-06 }, "TrainerController._save_models": { "total": 0.08457196599965755, "count": 1, "self": 0.0009384009999848786, "children": { "RLTrainer._checkpoint": { "total": 0.08363356499967267, "count": 1, "self": 0.08363356499967267 } } } } } } }