{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.895716667175293, "min": 0.895716667175293, "max": 2.8699827194213867, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8552.302734375, "min": 8552.302734375, "max": 29612.482421875, "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": 12.75611686706543, "min": 0.4630786180496216, "max": 12.75611686706543, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2487.44287109375, "min": 89.83724975585938, "max": 2571.162353515625, "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": 0.0675581138671345, "min": 0.06302075970112733, "max": 0.07654098398508687, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.270232455468538, "min": 0.25208303880450933, "max": 0.3706449043679373, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2280424298974229, "min": 0.11329146999610112, "max": 0.2874748522744459, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9121697195896916, "min": 0.4531658799844045, "max": 1.351610531701761, "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": 25.0, "min": 3.522727272727273, "max": 25.522727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 155.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.522727272727273, "max": 25.522727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 155.0, "max": 1375.0, "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": "1703352206", "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": "1703352686" }, "total": 480.01981692899994, "count": 1, "self": 0.4482096449999631, "children": { "run_training.setup": { "total": 0.055812357999968754, "count": 1, "self": 0.055812357999968754 }, "TrainerController.start_learning": { "total": 479.515794926, "count": 1, "self": 0.5919770459948381, "children": { "TrainerController._reset_env": { "total": 3.2658157439999513, "count": 1, "self": 3.2658157439999513 }, "TrainerController.advance": { "total": 475.56440713700516, "count": 18200, "self": 0.30370065800161683, "children": { "env_step": { "total": 475.26070647900355, "count": 18200, "self": 312.0358511700112, "children": { "SubprocessEnvManager._take_step": { "total": 162.92472769099544, "count": 18200, "self": 1.5669133549897083, "children": { "TorchPolicy.evaluate": { "total": 161.35781433600573, "count": 18200, "self": 161.35781433600573 } } }, "workers": { "total": 0.3001276179969068, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 477.92015739300103, "count": 18200, "is_parallel": true, "self": 237.9325346379976, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005622152000000824, "count": 1, "is_parallel": true, "self": 0.004142807000107496, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014793449998933283, "count": 10, "is_parallel": true, "self": 0.0014793449998933283 } } }, "UnityEnvironment.step": { "total": 0.07615196000000424, "count": 1, "is_parallel": true, "self": 0.0006524849999891558, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004195870000103241, "count": 1, "is_parallel": true, "self": 0.0004195870000103241 }, "communicator.exchange": { "total": 0.07270515199996908, "count": 1, "is_parallel": true, "self": 0.07270515199996908 }, "steps_from_proto": { "total": 0.002374736000035682, "count": 1, "is_parallel": true, "self": 0.00040787600005387503, "children": { "_process_rank_one_or_two_observation": { "total": 0.001966859999981807, "count": 10, "is_parallel": true, "self": 0.001966859999981807 } } } } } } }, "UnityEnvironment.step": { "total": 239.98762275500343, "count": 18199, "is_parallel": true, "self": 11.227318049009057, "children": { "UnityEnvironment._generate_step_input": { "total": 5.777411436991827, "count": 18199, "is_parallel": true, "self": 5.777411436991827 }, "communicator.exchange": { "total": 185.97337150499368, "count": 18199, "is_parallel": true, "self": 185.97337150499368 }, "steps_from_proto": { "total": 37.009521764008866, "count": 18199, "is_parallel": true, "self": 6.853298427998084, "children": { "_process_rank_one_or_two_observation": { "total": 30.156223336010783, "count": 181990, "is_parallel": true, "self": 30.156223336010783 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021199900004376104, "count": 1, "self": 0.00021199900004376104, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.3951904190044, "count": 709041, "is_parallel": true, "self": 15.41569408199166, "children": { "process_trajectory": { "total": 260.2385012750128, "count": 709041, "is_parallel": true, "self": 259.4406982300128, "children": { "RLTrainer._checkpoint": { "total": 0.7978030450000233, "count": 4, "is_parallel": true, "self": 0.7978030450000233 } } }, "_update_policy": { "total": 193.7409950619999, "count": 90, "is_parallel": true, "self": 61.182412975000375, "children": { "TorchPPOOptimizer.update": { "total": 132.55858208699954, "count": 4587, "is_parallel": true, "self": 132.55858208699954 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09338300000001709, "count": 1, "self": 0.001001043999963258, "children": { "RLTrainer._checkpoint": { "total": 0.09238195600005383, "count": 1, "self": 0.09238195600005383 } } } } } } }