{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9409710168838501, "min": 0.9409710168838501, "max": 2.8671975135803223, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8942.98828125, "min": 8942.98828125, "max": 29268.3515625, "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": 13.063539505004883, "min": 0.2504594027996063, "max": 13.063539505004883, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2547.39013671875, "min": 48.5891227722168, "max": 2664.22802734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07106391970242554, "min": 0.061110777769285696, "max": 0.07656111385257841, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28425567880970215, "min": 0.24444311107714278, "max": 0.37322506210858036, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21803751565954266, "min": 0.11034916368011824, "max": 0.30640532204917836, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8721500626381706, "min": 0.44139665472047296, "max": 1.5320266102458917, "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": 25.818181818181817, "min": 3.090909090909091, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 136.0, "max": 1424.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.090909090909091, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 136.0, "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": "1758995659", "python_version": "3.10.4 | packaged by conda-forge | (main, Mar 24 2022, 17:39:04) [GCC 10.3.0]", "command_line_arguments": "/usr/local/env/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": "1758996110" }, "total": 450.8144267330001, "count": 1, "self": 0.43082123700014563, "children": { "run_training.setup": { "total": 0.02029356299999563, "count": 1, "self": 0.02029356299999563 }, "TrainerController.start_learning": { "total": 450.363311933, "count": 1, "self": 0.37073274400813716, "children": { "TrainerController._reset_env": { "total": 2.82704584399994, "count": 1, "self": 2.82704584399994 }, "TrainerController.advance": { "total": 447.08929427599173, "count": 18192, "self": 0.4135261009766964, "children": { "env_step": { "total": 326.8143913590013, "count": 18192, "self": 255.91795938300947, "children": { "SubprocessEnvManager._take_step": { "total": 70.66442349600743, "count": 18192, "self": 1.2859656010011804, "children": { "TorchPolicy.evaluate": { "total": 69.37845789500625, "count": 18192, "self": 69.37845789500625 } } }, "workers": { "total": 0.23200847998441532, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 448.46398800098086, "count": 18192, "is_parallel": true, "self": 223.96684088197208, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0050389930001983885, "count": 1, "is_parallel": true, "self": 0.003390821000266442, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016481719999319466, "count": 10, "is_parallel": true, "self": 0.0016481719999319466 } } }, "UnityEnvironment.step": { "total": 0.03649973700021292, "count": 1, "is_parallel": true, "self": 0.0006209310001850099, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003983219999099674, "count": 1, "is_parallel": true, "self": 0.0003983219999099674 }, "communicator.exchange": { "total": 0.03346067999996194, "count": 1, "is_parallel": true, "self": 0.03346067999996194 }, "steps_from_proto": { "total": 0.0020198040001560003, "count": 1, "is_parallel": true, "self": 0.00043964099972981785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015801630004261824, "count": 10, "is_parallel": true, "self": 0.0015801630004261824 } } } } } } }, "UnityEnvironment.step": { "total": 224.4971471190088, "count": 18191, "is_parallel": true, "self": 10.498707679999143, "children": { "UnityEnvironment._generate_step_input": { "total": 5.57322547700619, "count": 18191, "is_parallel": true, "self": 5.57322547700619 }, "communicator.exchange": { "total": 171.02209004100428, "count": 18191, "is_parallel": true, "self": 171.02209004100428 }, "steps_from_proto": { "total": 37.40312392099918, "count": 18191, "is_parallel": true, "self": 6.838482153069663, "children": { "_process_rank_one_or_two_observation": { "total": 30.564641767929515, "count": 181910, "is_parallel": true, "self": 30.564641767929515 } } } } } } } } } } }, "trainer_advance": { "total": 119.86137681601372, "count": 18192, "self": 0.4496353250442553, "children": { "process_trajectory": { "total": 27.082325106968938, "count": 18192, "self": 26.69323496696893, "children": { "RLTrainer._checkpoint": { "total": 0.3890901400000075, "count": 4, "self": 0.3890901400000075 } } }, "_update_policy": { "total": 92.32941638400052, "count": 90, "self": 37.33584149600097, "children": { "TorchPPOOptimizer.update": { "total": 54.99357488799956, "count": 4587, "self": 54.99357488799956 } } } } } } }, "trainer_threads": { "total": 8.550000529794488e-07, "count": 1, "self": 8.550000529794488e-07 }, "TrainerController._save_models": { "total": 0.07623821400011366, "count": 1, "self": 0.0007315390000712796, "children": { "RLTrainer._checkpoint": { "total": 0.07550667500004238, "count": 1, "self": 0.07550667500004238 } } } } } } }