{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9268140196800232, "min": 0.9268140196800232, "max": 2.855933904647827, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8839.025390625, "min": 8839.025390625, "max": 29279.03515625, "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": 12.571138381958008, "min": 0.43291130661964417, "max": 12.571138381958008, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2451.3720703125, "min": 83.98479461669922, "max": 2533.017578125, "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": 0.06852294416703265, "min": 0.0643664756487352, "max": 0.07555206218708989, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2740917766681306, "min": 0.2574659025949408, "max": 0.37776031093544943, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1968971065738622, "min": 0.18861382280238995, "max": 0.28641239387147566, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7875884262954488, "min": 0.7544552912095598, "max": 1.4320619693573782, "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": 24.954545454545453, "min": 4.25, "max": 25.10909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 187.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 4.25, "max": 25.10909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 187.0, "max": 1381.0, "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": "1691511261", "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": "1691511744" }, "total": 483.1372813500002, "count": 1, "self": 0.4370653770001809, "children": { "run_training.setup": { "total": 0.043954155000164974, "count": 1, "self": 0.043954155000164974 }, "TrainerController.start_learning": { "total": 482.65626181799985, "count": 1, "self": 0.5749671340056466, "children": { "TrainerController._reset_env": { "total": 5.76555028100006, "count": 1, "self": 5.76555028100006 }, "TrainerController.advance": { "total": 476.1732656819943, "count": 18200, "self": 0.29236147198935214, "children": { "env_step": { "total": 475.8809042100049, "count": 18200, "self": 346.24379427998974, "children": { "SubprocessEnvManager._take_step": { "total": 129.3422109109813, "count": 18200, "self": 1.7552541689640293, "children": { "TorchPolicy.evaluate": { "total": 127.58695674201726, "count": 18200, "self": 127.58695674201726 } } }, "workers": { "total": 0.2948990190338918, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 480.96523598499584, "count": 18200, "is_parallel": true, "self": 227.02921690798416, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0071368840001468925, "count": 1, "is_parallel": true, "self": 0.005388241000218841, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017486429999280517, "count": 10, "is_parallel": true, "self": 0.0017486429999280517 } } }, "UnityEnvironment.step": { "total": 0.03755015799993089, "count": 1, "is_parallel": true, "self": 0.0006115869998666312, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000354626999978791, "count": 1, "is_parallel": true, "self": 0.000354626999978791 }, "communicator.exchange": { "total": 0.03305041500016159, "count": 1, "is_parallel": true, "self": 0.03305041500016159 }, "steps_from_proto": { "total": 0.003533528999923874, "count": 1, "is_parallel": true, "self": 0.00040505199990548135, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031284770000183926, "count": 10, "is_parallel": true, "self": 0.0031284770000183926 } } } } } } }, "UnityEnvironment.step": { "total": 253.93601907701168, "count": 18199, "is_parallel": true, "self": 10.669701483980816, "children": { "UnityEnvironment._generate_step_input": { "total": 5.404905561010764, "count": 18199, "is_parallel": true, "self": 5.404905561010764 }, "communicator.exchange": { "total": 201.3711725210253, "count": 18199, "is_parallel": true, "self": 201.3711725210253 }, "steps_from_proto": { "total": 36.4902395109948, "count": 18199, "is_parallel": true, "self": 6.753751256041369, "children": { "_process_rank_one_or_two_observation": { "total": 29.73648825495343, "count": 181990, "is_parallel": true, "self": 29.73648825495343 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.4939999977723346e-05, "count": 1, "self": 3.4939999977723346e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.5716126759662, "count": 451638, "is_parallel": true, "self": 10.01848530098573, "children": { "process_trajectory": { "total": 258.9374339869803, "count": 451638, "is_parallel": true, "self": 257.6804409699803, "children": { "RLTrainer._checkpoint": { "total": 1.2569930170000134, "count": 4, "is_parallel": true, "self": 1.2569930170000134 } } }, "_update_policy": { "total": 203.61569338800018, "count": 90, "is_parallel": true, "self": 79.83269887000642, "children": { "TorchPPOOptimizer.update": { "total": 123.78299451799376, "count": 4587, "is_parallel": true, "self": 123.78299451799376 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14244378099988353, "count": 1, "self": 0.0009293599998727586, "children": { "RLTrainer._checkpoint": { "total": 0.14151442100001077, "count": 1, "self": 0.14151442100001077 } } } } } } }