{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9931444525718689, "min": 0.9931444525718689, "max": 2.8684849739074707, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9493.4677734375, "min": 9493.4677734375, "max": 29376.154296875, "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": 12.903213500976562, "min": 0.34639227390289307, "max": 12.903213500976562, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.126708984375, "min": 67.20010375976562, "max": 2615.7607421875, "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": 0.07293553700474059, "min": 0.061731325333918605, "max": 0.07396709357748407, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29174214801896237, "min": 0.24692530133567442, "max": 0.36983546788742033, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19663269730175242, "min": 0.10974604453133674, "max": 0.29151341061966096, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7865307892070097, "min": 0.43898417812534696, "max": 1.4575670530983047, "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": 25.5, "min": 3.0454545454545454, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 134.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 3.0454545454545454, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 134.0, "max": 1401.0, "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": "1707489947", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707490378" }, "total": 431.103127857, "count": 1, "self": 0.437415867000027, "children": { "run_training.setup": { "total": 0.05000892999998996, "count": 1, "self": 0.05000892999998996 }, "TrainerController.start_learning": { "total": 430.61570306, "count": 1, "self": 0.528694401989469, "children": { "TrainerController._reset_env": { "total": 2.9963075260000096, "count": 1, "self": 2.9963075260000096 }, "TrainerController.advance": { "total": 427.0000313970105, "count": 18200, "self": 0.2590935119983442, "children": { "env_step": { "total": 426.74093788501216, "count": 18200, "self": 275.40655924901284, "children": { "SubprocessEnvManager._take_step": { "total": 151.06597585699728, "count": 18200, "self": 1.4026269559963112, "children": { "TorchPolicy.evaluate": { "total": 149.66334890100097, "count": 18200, "self": 149.66334890100097 } } }, "workers": { "total": 0.2684027790020309, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 429.4674122690009, "count": 18200, "is_parallel": true, "self": 213.5557462269985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006338278000043829, "count": 1, "is_parallel": true, "self": 0.004787623999959578, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015506540000842506, "count": 10, "is_parallel": true, "self": 0.0015506540000842506 } } }, "UnityEnvironment.step": { "total": 0.040061015999981464, "count": 1, "is_parallel": true, "self": 0.0006424139999126055, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041980299999977433, "count": 1, "is_parallel": true, "self": 0.00041980299999977433 }, "communicator.exchange": { "total": 0.03700493500002722, "count": 1, "is_parallel": true, "self": 0.03700493500002722 }, "steps_from_proto": { "total": 0.0019938640000418673, "count": 1, "is_parallel": true, "self": 0.00039816300011352723, "children": { "_process_rank_one_or_two_observation": { "total": 0.00159570099992834, "count": 10, "is_parallel": true, "self": 0.00159570099992834 } } } } } } }, "UnityEnvironment.step": { "total": 215.91166604200237, "count": 18199, "is_parallel": true, "self": 10.418296982993638, "children": { "UnityEnvironment._generate_step_input": { "total": 5.187643278000564, "count": 18199, "is_parallel": true, "self": 5.187643278000564 }, "communicator.exchange": { "total": 167.67629671700865, "count": 18199, "is_parallel": true, "self": 167.67629671700865 }, "steps_from_proto": { "total": 32.62942906399951, "count": 18199, "is_parallel": true, "self": 5.99496423098185, "children": { "_process_rank_one_or_two_observation": { "total": 26.63446483301766, "count": 181990, "is_parallel": true, "self": 26.63446483301766 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012385200000153418, "count": 1, "self": 0.00012385200000153418, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 421.60834207495213, "count": 652453, "is_parallel": true, "self": 13.536658652002643, "children": { "process_trajectory": { "total": 232.8316951959497, "count": 652453, "is_parallel": true, "self": 232.3264904819498, "children": { "RLTrainer._checkpoint": { "total": 0.5052047139998876, "count": 4, "is_parallel": true, "self": 0.5052047139998876 } } }, "_update_policy": { "total": 175.2399882269998, "count": 90, "is_parallel": true, "self": 50.577197391002755, "children": { "TorchPPOOptimizer.update": { "total": 124.66279083599704, "count": 4587, "is_parallel": true, "self": 124.66279083599704 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09054588300000432, "count": 1, "self": 0.0009118809999790756, "children": { "RLTrainer._checkpoint": { "total": 0.08963400200002525, "count": 1, "self": 0.08963400200002525 } } } } } } }