{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.816674530506134, "min": 0.7926225066184998, "max": 2.8568437099456787, "count": 36 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7743.7080078125, "min": 7741.38330078125, "max": 29256.9375, "count": 36 }, "SnowballTarget.Step.mean": { "value": 359944.0, "min": 9952.0, "max": 359944.0, "count": 36 }, "SnowballTarget.Step.sum": { "value": 359944.0, "min": 9952.0, "max": 359944.0, "count": 36 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.722535133361816, "min": 0.29261475801467896, "max": 13.722535133361816, "count": 36 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2662.171875, "min": 56.76726150512695, "max": 2802.098876953125, "count": 36 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 36 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 36 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06622977422118899, "min": 0.06128641730337061, "max": 0.0728793583022814, "count": 36 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26491909688475596, "min": 0.24921138306101553, "max": 0.364396791511407, "count": 36 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17329898845477432, "min": 0.1065496731236778, "max": 0.3044767375378048, "count": 36 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6931959538190973, "min": 0.4261986924947112, "max": 1.295578857555109, "count": 36 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.68728710424e-05, "min": 8.68728710424e-05, "max": 0.00029675280108239997, "count": 36 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003474914841696, "min": 0.0003474914841696, "max": 0.001454064015312, "count": 36 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1289576, "min": 0.1289576, "max": 0.19891759999999997, "count": 36 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5158304, "min": 0.5158304, "max": 0.984688, "count": 36 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0014549842400000002, "min": 0.0014549842400000002, "max": 0.00494598824, "count": 36 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005819936960000001, "min": 0.005819936960000001, "max": 0.0242359312, "count": 36 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.90909090909091, "min": 3.022727272727273, "max": 26.90909090909091, "count": 36 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1184.0, "min": 133.0, "max": 1480.0, "count": 36 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.90909090909091, "min": 3.022727272727273, "max": 26.90909090909091, "count": 36 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1184.0, "min": 133.0, "max": 1480.0, "count": 36 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714813702", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --force --run-id=SnowballTarget3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714814511" }, "total": 808.9773728229998, "count": 1, "self": 0.012453610999273224, "children": { "run_training.setup": { "total": 0.05065045300034399, "count": 1, "self": 0.05065045300034399 }, "TrainerController.start_learning": { "total": 808.9142687590002, "count": 1, "self": 1.9795725669919193, "children": { "TrainerController._reset_env": { "total": 2.5851128809999864, "count": 1, "self": 2.5851128809999864 }, "TrainerController.advance": { "total": 804.0989159740084, "count": 33001, "self": 0.4834191440154427, "children": { "env_step": { "total": 803.6154968299929, "count": 33001, "self": 520.7575256590162, "children": { "SubprocessEnvManager._take_step": { "total": 282.35716918894013, "count": 33001, "self": 2.5989544428734916, "children": { "TorchPolicy.evaluate": { "total": 279.75821474606664, "count": 33001, "self": 279.75821474606664 } } }, "workers": { "total": 0.5008019820365917, "count": 33000, "self": 0.0, "children": { "worker_root": { "total": 805.5951890579781, "count": 33000, "is_parallel": true, "self": 402.1318842810192, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032390200003646896, "count": 1, "is_parallel": true, "self": 0.0008766969999669527, "children": { "_process_rank_one_or_two_observation": { "total": 0.002362323000397737, "count": 10, "is_parallel": true, "self": 0.002362323000397737 } } }, "UnityEnvironment.step": { "total": 0.03659387499965305, "count": 1, "is_parallel": true, "self": 0.0006553569996867736, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003889899999194313, "count": 1, "is_parallel": true, "self": 0.0003889899999194313 }, "communicator.exchange": { "total": 0.0336073779999424, "count": 1, "is_parallel": true, "self": 0.0336073779999424 }, "steps_from_proto": { "total": 0.0019421500001044478, "count": 1, "is_parallel": true, "self": 0.0003677839999909338, "children": { "_process_rank_one_or_two_observation": { "total": 0.001574366000113514, "count": 10, "is_parallel": true, "self": 0.001574366000113514 } } } } } } }, "UnityEnvironment.step": { "total": 403.4633047769589, "count": 32999, "is_parallel": true, "self": 18.4526843290937, "children": { "UnityEnvironment._generate_step_input": { "total": 9.606960499925663, "count": 32999, "is_parallel": true, "self": 9.606960499925663 }, "communicator.exchange": { "total": 315.35880058793555, "count": 32999, "is_parallel": true, "self": 315.35880058793555 }, "steps_from_proto": { "total": 60.04485936000401, "count": 32999, "is_parallel": true, "self": 11.246593000818393, "children": { "_process_rank_one_or_two_observation": { "total": 48.79826635918562, "count": 329990, "is_parallel": true, "self": 48.79826635918562 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010824699984368635, "count": 1, "self": 0.00010824699984368635, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 794.0796448990204, "count": 1171886, "is_parallel": true, "self": 24.530406085900722, "children": { "process_trajectory": { "total": 437.4762247271183, "count": 1171887, "is_parallel": true, "self": 437.0641351051181, "children": { "RLTrainer._checkpoint": { "total": 0.41208962200016686, "count": 3, "is_parallel": true, "self": 0.41208962200016686 } } }, "_update_policy": { "total": 332.0730140860014, "count": 164, "is_parallel": true, "self": 97.32214598001883, "children": { "TorchPPOOptimizer.update": { "total": 234.7508681059826, "count": 8378, "is_parallel": true, "self": 234.7508681059826 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2505590900000243, "count": 1, "self": 0.001279290000184119, "children": { "RLTrainer._checkpoint": { "total": 0.24927979999984018, "count": 1, "self": 0.24927979999984018 } } } } } } }