{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8785006999969482, "min": 0.8760251402854919, "max": 2.2489287853240967, "count": 46 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8474.896484375, "min": 8474.896484375, "max": 20444.947265625, "count": 46 }, "SnowballTarget.Step.mean": { "value": 499952.0, "min": 49936.0, "max": 499952.0, "count": 46 }, "SnowballTarget.Step.sum": { "value": 499952.0, "min": 49936.0, "max": 499952.0, "count": 46 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.292645454406738, "min": 5.827279567718506, "max": 14.420307159423828, "count": 46 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2787.06591796875, "min": 844.9555053710938, "max": 2940.49462890625, "count": 46 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 46 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 6567.0, "max": 10945.0, "count": 46 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07369226362860383, "min": 0.05860852830057197, "max": 0.07806807999212668, "count": 46 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2947690545144153, "min": 0.19623087732607553, "max": 0.3746745030375143, "count": 46 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.12998476065695286, "min": 0.12520532667929052, "max": 0.24657660112077115, "count": 46 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5199390426278114, "min": 0.5008213067171621, "max": 1.2328830056038558, "count": 46 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.193698903200001e-06, "min": 2.193698903200001e-06, "max": 0.0001812736093632, "count": 46 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.774795612800005e-06, "min": 8.774795612800005e-06, "max": 0.0008711680644160002, "count": 46 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1010968, "min": 0.1010968, "max": 0.19063680000000005, "count": 46 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4043872, "min": 0.4043872, "max": 0.9355840000000001, "count": 46 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.473032000000003e-05, "min": 6.473032000000003e-05, "max": 0.00453277632, "count": 46 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00025892128000000014, "min": 0.00025892128000000014, "max": 0.0217856416, "count": 46 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.272727272727273, "min": 15.393939393939394, "max": 28.509090909090908, "count": 46 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1244.0, "min": 508.0, "max": 1568.0, "count": 46 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.272727272727273, "min": 15.393939393939394, "max": 28.509090909090908, "count": 46 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1244.0, "min": 508.0, "max": 1568.0, "count": 46 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 46 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713899334", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713900236" }, "total": 902.4398860050001, "count": 1, "self": 0.32148621200008165, "children": { "run_training.setup": { "total": 0.052702590999956556, "count": 1, "self": 0.052702590999956556 }, "TrainerController.start_learning": { "total": 902.065697202, "count": 1, "self": 1.047607644012487, "children": { "TrainerController._reset_env": { "total": 1.8630781790000128, "count": 1, "self": 1.8630781790000128 }, "TrainerController.advance": { "total": 899.0180193389875, "count": 41612, "self": 0.5070902269683302, "children": { "env_step": { "total": 898.5109291120192, "count": 41612, "self": 619.6688795220143, "children": { "SubprocessEnvManager._take_step": { "total": 278.32785056801345, "count": 41612, "self": 2.8185278930254754, "children": { "TorchPolicy.evaluate": { "total": 275.50932267498797, "count": 41612, "self": 275.50932267498797 } } }, "workers": { "total": 0.5141990219914305, "count": 41612, "self": 0.0, "children": { "worker_root": { "total": 900.6625719539838, "count": 41612, "is_parallel": true, "self": 473.5189549909878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022677320000639156, "count": 1, "is_parallel": true, "self": 0.000670738999929199, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015969930001347166, "count": 10, "is_parallel": true, "self": 0.0015969930001347166 } } }, "UnityEnvironment.step": { "total": 0.028552360000048793, "count": 1, "is_parallel": true, "self": 0.00045093900018855493, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004014699999288496, "count": 1, "is_parallel": true, "self": 0.0004014699999288496 }, "communicator.exchange": { "total": 0.02644259599992438, "count": 1, "is_parallel": true, "self": 0.02644259599992438 }, "steps_from_proto": { "total": 0.00125735500000701, "count": 1, "is_parallel": true, "self": 0.0002572660001760596, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010000889998309503, "count": 10, "is_parallel": true, "self": 0.0010000889998309503 } } } } } } }, "UnityEnvironment.step": { "total": 427.143616962996, "count": 41611, "is_parallel": true, "self": 15.177523103978729, "children": { "UnityEnvironment._generate_step_input": { "total": 8.136478518004083, "count": 41611, "is_parallel": true, "self": 8.136478518004083 }, "communicator.exchange": { "total": 354.27928298599454, "count": 41611, "is_parallel": true, "self": 354.27928298599454 }, "steps_from_proto": { "total": 49.55033235501867, "count": 41611, "is_parallel": true, "self": 9.535304745025655, "children": { "_process_rank_one_or_two_observation": { "total": 40.01502760999301, "count": 416110, "is_parallel": true, "self": 40.01502760999301 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012238500016792386, "count": 1, "self": 0.00012238500016792386, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 897.7540536789697, "count": 426923, "is_parallel": true, "self": 5.43576744600341, "children": { "process_trajectory": { "total": 538.2202289099657, "count": 426923, "is_parallel": true, "self": 536.4171077899658, "children": { "RLTrainer._checkpoint": { "total": 1.8031211199999007, "count": 10, "is_parallel": true, "self": 1.8031211199999007 } } }, "_update_policy": { "total": 354.0980573230006, "count": 207, "is_parallel": true, "self": 82.3815759209972, "children": { "TorchPPOOptimizer.update": { "total": 271.7164814020034, "count": 10548, "is_parallel": true, "self": 271.7164814020034 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13686965499982762, "count": 1, "self": 0.0015136479999000585, "children": { "RLTrainer._checkpoint": { "total": 0.13535600699992756, "count": 1, "self": 0.13535600699992756 } } } } } } }