{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8442969918251038, "min": 0.8442969918251038, "max": 2.8652215003967285, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8126.3583984375, "min": 8126.3583984375, "max": 29311.21484375, "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": 12.935904502868652, "min": 0.4348377287387848, "max": 12.935904502868652, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2522.50146484375, "min": 84.3585205078125, "max": 2614.8193359375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06659612313367189, "min": 0.05946831933843165, "max": 0.07634654625286988, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26638449253468754, "min": 0.2378732773537266, "max": 0.3491719665930849, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20340939209449524, "min": 0.11437556984966768, "max": 0.2667519511545406, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.813637568377981, "min": 0.4575022793986707, "max": 1.333759755772703, "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": 25.545454545454547, "min": 3.477272727272727, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1124.0, "min": 153.0, "max": 1420.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.545454545454547, "min": 3.477272727272727, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1124.0, "min": 153.0, "max": 1420.0, "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": "1720022772", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720023247" }, "total": 475.19624061499997, "count": 1, "self": 0.6971993980000093, "children": { "run_training.setup": { "total": 0.07349550300000374, "count": 1, "self": 0.07349550300000374 }, "TrainerController.start_learning": { "total": 474.42554571399995, "count": 1, "self": 0.6164748350032596, "children": { "TrainerController._reset_env": { "total": 3.0814580370000044, "count": 1, "self": 3.0814580370000044 }, "TrainerController.advance": { "total": 470.5712233709968, "count": 18219, "self": 0.29864626599737676, "children": { "env_step": { "total": 470.2725771049994, "count": 18219, "self": 307.03759175099674, "children": { "SubprocessEnvManager._take_step": { "total": 162.93396048500392, "count": 18219, "self": 1.5348843300104136, "children": { "TorchPolicy.evaluate": { "total": 161.3990761549935, "count": 18219, "self": 161.3990761549935 } } }, "workers": { "total": 0.301024868998752, "count": 18219, "self": 0.0, "children": { "worker_root": { "total": 473.13655143399444, "count": 18219, "is_parallel": true, "self": 237.36392053699166, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005283451999957833, "count": 1, "is_parallel": true, "self": 0.0036168439999642032, "children": { "_process_rank_one_or_two_observation": { "total": 0.00166660799999363, "count": 10, "is_parallel": true, "self": 0.00166660799999363 } } }, "UnityEnvironment.step": { "total": 0.040924885999970684, "count": 1, "is_parallel": true, "self": 0.0007234390000121493, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000411173999964376, "count": 1, "is_parallel": true, "self": 0.000411173999964376 }, "communicator.exchange": { "total": 0.03772839800001293, "count": 1, "is_parallel": true, "self": 0.03772839800001293 }, "steps_from_proto": { "total": 0.002061874999981228, "count": 1, "is_parallel": true, "self": 0.00040165900003330535, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016602159999479227, "count": 10, "is_parallel": true, "self": 0.0016602159999479227 } } } } } } }, "UnityEnvironment.step": { "total": 235.77263089700278, "count": 18218, "is_parallel": true, "self": 10.752526461008642, "children": { "UnityEnvironment._generate_step_input": { "total": 5.579830431997664, "count": 18218, "is_parallel": true, "self": 5.579830431997664 }, "communicator.exchange": { "total": 184.36585859200324, "count": 18218, "is_parallel": true, "self": 184.36585859200324 }, "steps_from_proto": { "total": 35.07441541199324, "count": 18218, "is_parallel": true, "self": 6.771882603999927, "children": { "_process_rank_one_or_two_observation": { "total": 28.302532807993316, "count": 182180, "is_parallel": true, "self": 28.302532807993316 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014230299996143003, "count": 1, "self": 0.00014230299996143003, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 464.6234167089993, "count": 712311, "is_parallel": true, "self": 15.215650759001619, "children": { "process_trajectory": { "total": 256.3155497149975, "count": 712311, "is_parallel": true, "self": 255.13250996599737, "children": { "RLTrainer._checkpoint": { "total": 1.183039749000102, "count": 4, "is_parallel": true, "self": 1.183039749000102 } } }, "_update_policy": { "total": 193.0922162350002, "count": 90, "is_parallel": true, "self": 61.44213417300318, "children": { "TorchPPOOptimizer.update": { "total": 131.650082061997, "count": 4587, "is_parallel": true, "self": 131.650082061997 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1562471679999362, "count": 1, "self": 0.0013649829999167196, "children": { "RLTrainer._checkpoint": { "total": 0.1548821850000195, "count": 1, "self": 0.1548821850000195 } } } } } } }