{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9247990846633911, "min": 0.9247990846633911, "max": 2.84659481048584, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8880.845703125, "min": 8880.845703125, "max": 29277.228515625, "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": 12.677482604980469, "min": 0.2984957993030548, "max": 12.677482604980469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2472.109130859375, "min": 57.90818405151367, "max": 2557.306396484375, "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": 0.06817100967928841, "min": 0.06239838545885754, "max": 0.07424634718050833, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27268403871715363, "min": 0.2558727440083007, "max": 0.3600273628327676, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20365881503504865, "min": 0.11646885974515303, "max": 0.2637534755117753, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8146352601401946, "min": 0.4658754389806121, "max": 1.3104284245009514, "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": 25.40909090909091, "min": 3.1818181818181817, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 140.0, "max": 1365.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.1818181818181817, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 140.0, "max": 1365.0, "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": "1709198108", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/uoch/tf/bin/mlagents-learn config/ppo/SnowballTarget.yaml --env=training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1709198328" }, "total": 220.32709111700024, "count": 1, "self": 0.22014856500118185, "children": { "run_training.setup": { "total": 0.01653705499938951, "count": 1, "self": 0.01653705499938951 }, "TrainerController.start_learning": { "total": 220.09040549699967, "count": 1, "self": 0.35361847499370924, "children": { "TrainerController._reset_env": { "total": 0.9062590699995781, "count": 1, "self": 0.9062590699995781 }, "TrainerController.advance": { "total": 218.77896366900768, "count": 18205, "self": 0.15236830203684804, "children": { "env_step": { "total": 218.62659536697083, "count": 18205, "self": 139.5606353679268, "children": { "SubprocessEnvManager._take_step": { "total": 78.89927477697256, "count": 18205, "self": 0.7515098539988685, "children": { "TorchPolicy.evaluate": { "total": 78.14776492297369, "count": 18205, "self": 78.14776492297369 } } }, "workers": { "total": 0.16668522207146452, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 219.7216914650271, "count": 18205, "is_parallel": true, "self": 124.8872568349725, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009512309998171986, "count": 1, "is_parallel": true, "self": 0.00023792899901309283, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007133020008041058, "count": 10, "is_parallel": true, "self": 0.0007133020008041058 } } }, "UnityEnvironment.step": { "total": 0.014846459999716899, "count": 1, "is_parallel": true, "self": 0.00020526799926301464, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017212300008395687, "count": 1, "is_parallel": true, "self": 0.00017212300008395687 }, "communicator.exchange": { "total": 0.01383044400063227, "count": 1, "is_parallel": true, "self": 0.01383044400063227 }, "steps_from_proto": { "total": 0.0006386249997376581, "count": 1, "is_parallel": true, "self": 0.00014495899904432008, "children": { "_process_rank_one_or_two_observation": { "total": 0.000493666000693338, "count": 10, "is_parallel": true, "self": 0.000493666000693338 } } } } } } }, "UnityEnvironment.step": { "total": 94.8344346300546, "count": 18204, "is_parallel": true, "self": 3.8753062118857997, "children": { "UnityEnvironment._generate_step_input": { "total": 2.2230142600246836, "count": 18204, "is_parallel": true, "self": 2.2230142600246836 }, "communicator.exchange": { "total": 76.39028252107437, "count": 18204, "is_parallel": true, "self": 76.39028252107437 }, "steps_from_proto": { "total": 12.34583163706975, "count": 18204, "is_parallel": true, "self": 2.4896941540364423, "children": { "_process_rank_one_or_two_observation": { "total": 9.856137483033308, "count": 182040, "is_parallel": true, "self": 9.856137483033308 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011099399944214383, "count": 1, "self": 0.00011099399944214383, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 218.63712701402346, "count": 159627, "is_parallel": true, "self": 1.2092210750461163, "children": { "process_trajectory": { "total": 119.31616653297806, "count": 159627, "is_parallel": true, "self": 119.03014217098007, "children": { "RLTrainer._checkpoint": { "total": 0.2860243619979883, "count": 4, "is_parallel": true, "self": 0.2860243619979883 } } }, "_update_policy": { "total": 98.11173940599929, "count": 90, "is_parallel": true, "self": 27.4225028020237, "children": { "TorchPPOOptimizer.update": { "total": 70.68923660397559, "count": 4587, "is_parallel": true, "self": 70.68923660397559 } } } } } } } } }, "TrainerController._save_models": { "total": 0.051453288999255165, "count": 1, "self": 0.0007764819993099081, "children": { "RLTrainer._checkpoint": { "total": 0.050676806999945256, "count": 1, "self": 0.050676806999945256 } } } } } } }