{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.037601113319397, "min": 1.0296074151992798, "max": 2.8538668155670166, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9907.015625, "min": 9907.015625, "max": 29257.84375, "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": 12.747821807861328, "min": 0.5159427523612976, "max": 12.747821807861328, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2485.8251953125, "min": 100.0928955078125, "max": 2552.845458984375, "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.Losses.PolicyLoss.mean": { "value": 0.06807527593980243, "min": 0.06115243420764968, "max": 0.0755657120159038, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27230110375920974, "min": 0.24460973683059872, "max": 0.377828560079519, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19465862294914674, "min": 0.16370460373696452, "max": 0.30557255564797225, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.778634491796587, "min": 0.6548184149478581, "max": 1.5278627782398613, "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.CumulativeReward.mean": { "value": 25.568181818181817, "min": 3.8181818181818183, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 168.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 3.8181818181818183, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 168.0, "max": 1379.0, "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": "1705503515", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705503953" }, "total": 437.68537885599994, "count": 1, "self": 0.4392265409999254, "children": { "run_training.setup": { "total": 0.06088569999997162, "count": 1, "self": 0.06088569999997162 }, "TrainerController.start_learning": { "total": 437.18526661500005, "count": 1, "self": 0.5322205089901217, "children": { "TrainerController._reset_env": { "total": 3.1672661759998846, "count": 1, "self": 3.1672661759998846 }, "TrainerController.advance": { "total": 433.40009987201006, "count": 18199, "self": 0.24530186300648893, "children": { "env_step": { "total": 433.15479800900357, "count": 18199, "self": 285.2464585159944, "children": { "SubprocessEnvManager._take_step": { "total": 147.64093629701438, "count": 18199, "self": 1.393612191018292, "children": { "TorchPolicy.evaluate": { "total": 146.24732410599609, "count": 18199, "self": 146.24732410599609 } } }, "workers": { "total": 0.26740319599480245, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 436.02017239900397, "count": 18199, "is_parallel": true, "self": 214.94411716200557, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0040299350000623235, "count": 1, "is_parallel": true, "self": 0.0026626559995293064, "children": { "_process_rank_one_or_two_observation": { "total": 0.001367279000533017, "count": 10, "is_parallel": true, "self": 0.001367279000533017 } } }, "UnityEnvironment.step": { "total": 0.03773443399995813, "count": 1, "is_parallel": true, "self": 0.0006508969997867098, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004994959999748971, "count": 1, "is_parallel": true, "self": 0.0004994959999748971 }, "communicator.exchange": { "total": 0.0342743580001752, "count": 1, "is_parallel": true, "self": 0.0342743580001752 }, "steps_from_proto": { "total": 0.002309683000021323, "count": 1, "is_parallel": true, "self": 0.000402418000248872, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019072649997724511, "count": 10, "is_parallel": true, "self": 0.0019072649997724511 } } } } } } }, "UnityEnvironment.step": { "total": 221.0760552369984, "count": 18198, "is_parallel": true, "self": 10.541730748026794, "children": { "UnityEnvironment._generate_step_input": { "total": 5.239345562992185, "count": 18198, "is_parallel": true, "self": 5.239345562992185 }, "communicator.exchange": { "total": 172.62905478599419, "count": 18198, "is_parallel": true, "self": 172.62905478599419 }, "steps_from_proto": { "total": 32.665924139985236, "count": 18198, "is_parallel": true, "self": 6.0457191529537795, "children": { "_process_rank_one_or_two_observation": { "total": 26.620204987031457, "count": 181980, "is_parallel": true, "self": 26.620204987031457 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016240600007222383, "count": 1, "self": 0.00016240600007222383, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 428.20798886504576, "count": 642685, "is_parallel": true, "self": 13.35505714015153, "children": { "process_trajectory": { "total": 236.8500192748943, "count": 642685, "is_parallel": true, "self": 235.88260740789428, "children": { "RLTrainer._checkpoint": { "total": 0.9674118670000098, "count": 4, "is_parallel": true, "self": 0.9674118670000098 } } }, "_update_policy": { "total": 178.00291244999994, "count": 90, "is_parallel": true, "self": 54.48543580300225, "children": { "TorchPPOOptimizer.update": { "total": 123.5174766469977, "count": 4584, "is_parallel": true, "self": 123.5174766469977 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08551765199990768, "count": 1, "self": 0.0009763049997673079, "children": { "RLTrainer._checkpoint": { "total": 0.08454134700014038, "count": 1, "self": 0.08454134700014038 } } } } } } }