{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9028151035308838, "min": 0.9028151035308838, "max": 2.8584086894989014, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8580.3544921875, "min": 8580.3544921875, "max": 29178.63671875, "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": 13.10327434539795, "min": 0.21839548647403717, "max": 13.10327434539795, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2555.138427734375, "min": 42.36872482299805, "max": 2649.470703125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07142895189349029, "min": 0.06324780893662726, "max": 0.07256227409394057, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28571580757396114, "min": 0.25299123574650906, "max": 0.35195700507428423, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20007185068200614, "min": 0.11536088001037784, "max": 0.3038554372740727, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8002874027280246, "min": 0.46144352004151135, "max": 1.4563571737677445, "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.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.Environment.CumulativeReward.mean": { "value": 25.40909090909091, "min": 3.25, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 143.0, "max": 1424.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.25, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 143.0, "max": 1424.0, "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": "1784538995", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1784539518" }, "total": 523.3247578900002, "count": 1, "self": 0.4843384450002759, "children": { "run_training.setup": { "total": 0.0413722850000795, "count": 1, "self": 0.0413722850000795 }, "TrainerController.start_learning": { "total": 522.7990471599999, "count": 1, "self": 0.46870490093670014, "children": { "TrainerController._reset_env": { "total": 3.1005674009998074, "count": 1, "self": 3.1005674009998074 }, "TrainerController.advance": { "total": 519.1309227320633, "count": 18192, "self": 0.4873100290446928, "children": { "env_step": { "total": 387.222112401043, "count": 18192, "self": 304.6054999850012, "children": { "SubprocessEnvManager._take_step": { "total": 82.32485413600693, "count": 18192, "self": 1.5600026400170464, "children": { "TorchPolicy.evaluate": { "total": 80.76485149598989, "count": 18192, "self": 80.76485149598989 } } }, "workers": { "total": 0.2917582800348555, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 520.6711827430097, "count": 18192, "is_parallel": true, "self": 254.38774731000603, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005186166999919806, "count": 1, "is_parallel": true, "self": 0.0034739840000383992, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017121829998814064, "count": 10, "is_parallel": true, "self": 0.0017121829998814064 } } }, "UnityEnvironment.step": { "total": 0.09396610099997815, "count": 1, "is_parallel": true, "self": 0.0006386849997852551, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003720490001342114, "count": 1, "is_parallel": true, "self": 0.0003720490001342114 }, "communicator.exchange": { "total": 0.08864248800000496, "count": 1, "is_parallel": true, "self": 0.08864248800000496 }, "steps_from_proto": { "total": 0.0043128790000537265, "count": 1, "is_parallel": true, "self": 0.00046191700016606774, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038509619998876587, "count": 10, "is_parallel": true, "self": 0.0038509619998876587 } } } } } } }, "UnityEnvironment.step": { "total": 266.28343543300366, "count": 18191, "is_parallel": true, "self": 11.90475594596387, "children": { "UnityEnvironment._generate_step_input": { "total": 6.362160015055451, "count": 18191, "is_parallel": true, "self": 6.362160015055451 }, "communicator.exchange": { "total": 204.14188747800767, "count": 18191, "is_parallel": true, "self": 204.14188747800767 }, "steps_from_proto": { "total": 43.874631993976664, "count": 18191, "is_parallel": true, "self": 7.544617594971669, "children": { "_process_rank_one_or_two_observation": { "total": 36.330014399004995, "count": 181910, "is_parallel": true, "self": 36.330014399004995 } } } } } } } } } } }, "trainer_advance": { "total": 131.42150030197558, "count": 18192, "self": 0.6151398559943573, "children": { "process_trajectory": { "total": 27.349528765980494, "count": 18192, "self": 26.87835909198043, "children": { "RLTrainer._checkpoint": { "total": 0.47116967400006615, "count": 4, "self": 0.47116967400006615 } } }, "_update_policy": { "total": 103.45683168000073, "count": 90, "self": 42.951342807016545, "children": { "TorchPPOOptimizer.update": { "total": 60.50548887298419, "count": 4587, "self": 60.50548887298419 } } } } } } }, "trainer_threads": { "total": 1.2479999895731453e-06, "count": 1, "self": 1.2479999895731453e-06 }, "TrainerController._save_models": { "total": 0.09885087800012116, "count": 1, "self": 0.001033921999805898, "children": { "RLTrainer._checkpoint": { "total": 0.09781695600031526, "count": 1, "self": 0.09781695600031526 } } } } } } }