{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9865582585334778, "min": 0.9865582585334778, "max": 2.863497495651245, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9452.21484375, "min": 9452.21484375, "max": 29356.576171875, "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": 11.601349830627441, "min": 0.3637205958366394, "max": 11.601349830627441, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2262.26318359375, "min": 70.56179809570312, "max": 2338.87548828125, "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": 0.07271999421523195, "min": 0.06305504692330335, "max": 0.07271999421523195, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2908799768609278, "min": 0.2545073831444789, "max": 0.35865301128811267, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18975376907516928, "min": 0.15093761827344732, "max": 0.26816518055457694, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7590150763006771, "min": 0.6037504730937893, "max": 1.3408259027728848, "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": 23.045454545454547, "min": 3.4318181818181817, "max": 23.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1014.0, "min": 151.0, "max": 1278.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.045454545454547, "min": 3.4318181818181817, "max": 23.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1014.0, "min": 151.0, "max": 1278.0, "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": "1692625494", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692626058" }, "total": 564.507415659, "count": 1, "self": 0.8358345230000168, "children": { "run_training.setup": { "total": 0.056806470000026366, "count": 1, "self": 0.056806470000026366 }, "TrainerController.start_learning": { "total": 563.6147746659999, "count": 1, "self": 0.7369128069911994, "children": { "TrainerController._reset_env": { "total": 4.774562586000002, "count": 1, "self": 4.774562586000002 }, "TrainerController.advance": { "total": 557.8333970340087, "count": 18215, "self": 0.3623862270009113, "children": { "env_step": { "total": 557.4710108070078, "count": 18215, "self": 407.2267137920063, "children": { "SubprocessEnvManager._take_step": { "total": 149.8668728380057, "count": 18215, "self": 2.149635852008032, "children": { "TorchPolicy.evaluate": { "total": 147.71723698599766, "count": 18215, "self": 147.71723698599766 } } }, "workers": { "total": 0.37742417699581665, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 561.4513323520064, "count": 18215, "is_parallel": true, "self": 255.450201120011, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006831284999975651, "count": 1, "is_parallel": true, "self": 0.004976004999946326, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018552800000293246, "count": 10, "is_parallel": true, "self": 0.0018552800000293246 } } }, "UnityEnvironment.step": { "total": 0.12336203700004944, "count": 1, "is_parallel": true, "self": 0.0007101759999841306, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004345890000081454, "count": 1, "is_parallel": true, "self": 0.0004345890000081454 }, "communicator.exchange": { "total": 0.11120693500004109, "count": 1, "is_parallel": true, "self": 0.11120693500004109 }, "steps_from_proto": { "total": 0.01101033700001608, "count": 1, "is_parallel": true, "self": 0.0004886520000013661, "children": { "_process_rank_one_or_two_observation": { "total": 0.010521685000014713, "count": 10, "is_parallel": true, "self": 0.010521685000014713 } } } } } } }, "UnityEnvironment.step": { "total": 306.0011312319954, "count": 18214, "is_parallel": true, "self": 12.708660798000722, "children": { "UnityEnvironment._generate_step_input": { "total": 6.395673072999045, "count": 18214, "is_parallel": true, "self": 6.395673072999045 }, "communicator.exchange": { "total": 241.70602353099713, "count": 18214, "is_parallel": true, "self": 241.70602353099713 }, "steps_from_proto": { "total": 45.19077382999848, "count": 18214, "is_parallel": true, "self": 8.781493209001894, "children": { "_process_rank_one_or_two_observation": { "total": 36.40928062099658, "count": 182140, "is_parallel": true, "self": 36.40928062099658 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021390799997789145, "count": 1, "self": 0.00021390799997789145, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 553.3826464509743, "count": 537444, "is_parallel": true, "self": 12.401136583923062, "children": { "process_trajectory": { "total": 309.4643759190517, "count": 537444, "is_parallel": true, "self": 308.2356555430516, "children": { "RLTrainer._checkpoint": { "total": 1.2287203760000693, "count": 4, "is_parallel": true, "self": 1.2287203760000693 } } }, "_update_policy": { "total": 231.51713394799964, "count": 90, "is_parallel": true, "self": 86.32065165500217, "children": { "TorchPPOOptimizer.update": { "total": 145.19648229299747, "count": 4587, "is_parallel": true, "self": 145.19648229299747 } } } } } } } } }, "TrainerController._save_models": { "total": 0.26968833099999756, "count": 1, "self": 0.0014025880000190227, "children": { "RLTrainer._checkpoint": { "total": 0.26828574299997854, "count": 1, "self": 0.26828574299997854 } } } } } } }