{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.573487639427185, "min": 1.573487639427185, "max": 2.8761613368988037, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 16200.62890625, "min": 14963.7421875, "max": 29359.85546875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.718636512756348, "min": 0.32245951890945435, "max": 8.718636512756348, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1778.601806640625, "min": 62.55714416503906, "max": 1778.601806640625, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07424881902966173, "min": 0.061684060014907595, "max": 0.07497731710877725, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.37124409514830864, "min": 0.24673624005963038, "max": 0.37124409514830864, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23538870793931627, "min": 0.11841491925274478, "max": 0.25669917288948507, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1769435396965813, "min": 0.4736596770109791, "max": 1.2637465981876148, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 18.8, "min": 3.0681818181818183, "max": 18.8, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1034.0, "min": 135.0, "max": 1034.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 18.8, "min": 3.0681818181818183, "max": 18.8, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1034.0, "min": 135.0, "max": 1034.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1776527318", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1776527562" }, "total": 243.84068069400018, "count": 1, "self": 0.4290487669995855, "children": { "run_training.setup": { "total": 0.03458013900035439, "count": 1, "self": 0.03458013900035439 }, "TrainerController.start_learning": { "total": 243.37705178800024, "count": 1, "self": 0.2059870430475712, "children": { "TrainerController._reset_env": { "total": 2.337898382000276, "count": 1, "self": 2.337898382000276 }, "TrainerController.advance": { "total": 240.75306095495216, "count": 9128, "self": 0.20481485200070892, "children": { "env_step": { "total": 175.94484463094432, "count": 9128, "self": 137.35375221189042, "children": { "SubprocessEnvManager._take_step": { "total": 38.46986799307888, "count": 9128, "self": 0.6955920721275106, "children": { "TorchPolicy.evaluate": { "total": 37.77427592095137, "count": 9128, "self": 37.77427592095137 } } }, "workers": { "total": 0.12122442597501504, "count": 9128, "self": 0.0, "children": { "worker_root": { "total": 242.3416572780261, "count": 9128, "is_parallel": true, "self": 121.71412224201686, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00319536499955575, "count": 1, "is_parallel": true, "self": 0.000905491999219521, "children": { "_process_rank_one_or_two_observation": { "total": 0.002289873000336229, "count": 10, "is_parallel": true, "self": 0.002289873000336229 } } }, "UnityEnvironment.step": { "total": 0.038202550999812956, "count": 1, "is_parallel": true, "self": 0.0006253510000533424, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003725460001078318, "count": 1, "is_parallel": true, "self": 0.0003725460001078318 }, "communicator.exchange": { "total": 0.034921438000310445, "count": 1, "is_parallel": true, "self": 0.034921438000310445 }, "steps_from_proto": { "total": 0.002283215999341337, "count": 1, "is_parallel": true, "self": 0.00040515999717172235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018780560021696147, "count": 10, "is_parallel": true, "self": 0.0018780560021696147 } } } } } } }, "UnityEnvironment.step": { "total": 120.62753503600925, "count": 9127, "is_parallel": true, "self": 5.546898582032554, "children": { "UnityEnvironment._generate_step_input": { "total": 3.0106750780223592, "count": 9127, "is_parallel": true, "self": 3.0106750780223592 }, "communicator.exchange": { "total": 91.59472575293785, "count": 9127, "is_parallel": true, "self": 91.59472575293785 }, "steps_from_proto": { "total": 20.475235623016488, "count": 9127, "is_parallel": true, "self": 3.5147007491759723, "children": { "_process_rank_one_or_two_observation": { "total": 16.960534873840516, "count": 91270, "is_parallel": true, "self": 16.960534873840516 } } } } } } } } } } }, "trainer_advance": { "total": 64.60340147200714, "count": 9128, "self": 0.23924088798594312, "children": { "process_trajectory": { "total": 14.66892492902116, "count": 9128, "self": 14.082356577022438, "children": { "RLTrainer._checkpoint": { "total": 0.5865683519987215, "count": 5, "self": 0.5865683519987215 } } }, "_update_policy": { "total": 49.69523565500003, "count": 45, "self": 20.394936241015785, "children": { "TorchPPOOptimizer.update": { "total": 29.30029941398425, "count": 2292, "self": 29.30029941398425 } } } } } } }, "trainer_threads": { "total": 9.630002750782296e-07, "count": 1, "self": 9.630002750782296e-07 }, "TrainerController._save_models": { "total": 0.08010444499996083, "count": 1, "self": 0.0009247460002370644, "children": { "RLTrainer._checkpoint": { "total": 0.07917969899972377, "count": 1, "self": 0.07917969899972377 } } } } } } }