{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.752148449420929, "min": 0.752148449420929, "max": 2.8483641147613525, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7189.787109375, "min": 7189.787109375, "max": 29170.095703125, "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": 12.818103790283203, "min": 0.28783854842185974, "max": 12.861093521118164, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.5302734375, "min": 55.84067916870117, "max": 2623.6630859375, "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": 0.07167294483024664, "min": 0.06363765849533842, "max": 0.0766985663817739, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28669177932098655, "min": 0.259535127135642, "max": 0.3541174422887921, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20099367208632768, "min": 0.11863694620642848, "max": 0.312313207750227, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8039746883453107, "min": 0.4745477848257139, "max": 1.561566038751135, "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": 25.068181818181817, "min": 3.272727272727273, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 144.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 3.272727272727273, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 144.0, "max": 1381.0, "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": "1705995407", "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": "1705995875" }, "total": 468.025880768, "count": 1, "self": 0.44039564000001974, "children": { "run_training.setup": { "total": 0.05359324500000184, "count": 1, "self": 0.05359324500000184 }, "TrainerController.start_learning": { "total": 467.53189188299996, "count": 1, "self": 0.6572246229972052, "children": { "TrainerController._reset_env": { "total": 3.3707300050000413, "count": 1, "self": 3.3707300050000413 }, "TrainerController.advance": { "total": 463.4119749600027, "count": 18200, "self": 0.3098688710043689, "children": { "env_step": { "total": 463.1021060889983, "count": 18200, "self": 305.2907937159897, "children": { "SubprocessEnvManager._take_step": { "total": 157.50242434600113, "count": 18200, "self": 1.5528202989936517, "children": { "TorchPolicy.evaluate": { "total": 155.94960404700748, "count": 18200, "self": 155.94960404700748 } } }, "workers": { "total": 0.30888802700746965, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 466.2380971479872, "count": 18200, "is_parallel": true, "self": 228.0327682789923, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0049494419999973616, "count": 1, "is_parallel": true, "self": 0.003509076999989702, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014403650000076595, "count": 10, "is_parallel": true, "self": 0.0014403650000076595 } } }, "UnityEnvironment.step": { "total": 0.04016439300005459, "count": 1, "is_parallel": true, "self": 0.0007411420001517399, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004266839999900185, "count": 1, "is_parallel": true, "self": 0.0004266839999900185 }, "communicator.exchange": { "total": 0.036938090999910855, "count": 1, "is_parallel": true, "self": 0.036938090999910855 }, "steps_from_proto": { "total": 0.002058476000001974, "count": 1, "is_parallel": true, "self": 0.0004228139997621838, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016356620002397904, "count": 10, "is_parallel": true, "self": 0.0016356620002397904 } } } } } } }, "UnityEnvironment.step": { "total": 238.2053288689949, "count": 18199, "is_parallel": true, "self": 11.200909404007461, "children": { "UnityEnvironment._generate_step_input": { "total": 5.497650760987199, "count": 18199, "is_parallel": true, "self": 5.497650760987199 }, "communicator.exchange": { "total": 186.83554578699795, "count": 18199, "is_parallel": true, "self": 186.83554578699795 }, "steps_from_proto": { "total": 34.6712229170023, "count": 18199, "is_parallel": true, "self": 6.559225286032529, "children": { "_process_rank_one_or_two_observation": { "total": 28.111997630969768, "count": 181990, "is_parallel": true, "self": 28.111997630969768 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.8793999920017086e-05, "count": 1, "self": 3.8793999920017086e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.72462636291516, "count": 705646, "is_parallel": true, "self": 14.806483668886472, "children": { "process_trajectory": { "total": 253.99229330902835, "count": 705646, "is_parallel": true, "self": 253.14191288002849, "children": { "RLTrainer._checkpoint": { "total": 0.8503804289998698, "count": 4, "is_parallel": true, "self": 0.8503804289998698 } } }, "_update_policy": { "total": 188.92584938500033, "count": 90, "is_parallel": true, "self": 57.759350248002306, "children": { "TorchPPOOptimizer.update": { "total": 131.16649913699803, "count": 4587, "is_parallel": true, "self": 131.16649913699803 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09192350100011026, "count": 1, "self": 0.0010119720000147936, "children": { "RLTrainer._checkpoint": { "total": 0.09091152900009547, "count": 1, "self": 0.09091152900009547 } } } } } } }