{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1693555116653442, "min": 1.1693555116653442, "max": 2.8793978691101074, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11165.005859375, "min": 11165.005859375, "max": 29487.9140625, "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": 12.097582817077637, "min": 0.26606428623199463, "max": 12.097582817077637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2359.028564453125, "min": 51.61647415161133, "max": 2423.43701171875, "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": 0.06938062583403913, "min": 0.06385078223127708, "max": 0.07462975741478195, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2775225033361565, "min": 0.2554031289251083, "max": 0.37314878707390975, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.13956210795132554, "min": 0.06211323528516326, "max": 0.1639507270034622, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5582484318053021, "min": 0.24845294114065303, "max": 0.8197536350173109, "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": 0.09999999999999998, "min": 0.09999999999999998, "max": 0.09999999999999998, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.3999999999999999, "min": 0.3999999999999999, "max": 0.4999999999999999, "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": 24.84090909090909, "min": 3.022727272727273, "max": 24.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 133.0, "max": 1341.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 3.022727272727273, "max": 24.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 133.0, "max": 1341.0, "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": "1673390957", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673391399" }, "total": 441.74680962, "count": 1, "self": 0.3869190840000556, "children": { "run_training.setup": { "total": 0.10603319400001965, "count": 1, "self": 0.10603319400001965 }, "TrainerController.start_learning": { "total": 441.25385734199995, "count": 1, "self": 0.5584747610053, "children": { "TrainerController._reset_env": { "total": 7.827061834999995, "count": 1, "self": 7.827061834999995 }, "TrainerController.advance": { "total": 432.7413921579947, "count": 18203, "self": 0.28471337199351865, "children": { "env_step": { "total": 432.4566787860012, "count": 18203, "self": 283.33638889400305, "children": { "SubprocessEnvManager._take_step": { "total": 148.8422044379991, "count": 18203, "self": 1.4327151819951496, "children": { "TorchPolicy.evaluate": { "total": 147.40948925600395, "count": 18203, "self": 34.02922643600044, "children": { "TorchPolicy.sample_actions": { "total": 113.38026282000351, "count": 18203, "self": 113.38026282000351 } } } } }, "workers": { "total": 0.27808545399904006, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 439.9892828069934, "count": 18203, "is_parallel": true, "self": 214.04782768799168, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005921063000016602, "count": 1, "is_parallel": true, "self": 0.0036898589999623255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022312040000542765, "count": 10, "is_parallel": true, "self": 0.0022312040000542765 } } }, "UnityEnvironment.step": { "total": 0.03582238499996038, "count": 1, "is_parallel": true, "self": 0.00044621899996855063, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029788500000904605, "count": 1, "is_parallel": true, "self": 0.00029788500000904605 }, "communicator.exchange": { "total": 0.03310262799999464, "count": 1, "is_parallel": true, "self": 0.03310262799999464 }, "steps_from_proto": { "total": 0.0019756529999881423, "count": 1, "is_parallel": true, "self": 0.00044814800003223354, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015275049999559087, "count": 10, "is_parallel": true, "self": 0.0015275049999559087 } } } } } } }, "UnityEnvironment.step": { "total": 225.94145511900172, "count": 18202, "is_parallel": true, "self": 8.532854514997894, "children": { "UnityEnvironment._generate_step_input": { "total": 5.156164746996865, "count": 18202, "is_parallel": true, "self": 5.156164746996865 }, "communicator.exchange": { "total": 180.3429908749987, "count": 18202, "is_parallel": true, "self": 180.3429908749987 }, "steps_from_proto": { "total": 31.909444982008267, "count": 18202, "is_parallel": true, "self": 6.849372103998633, "children": { "_process_rank_one_or_two_observation": { "total": 25.060072878009635, "count": 182020, "is_parallel": true, "self": 25.060072878009635 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.1988000020865e-05, "count": 1, "self": 4.1988000020865e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 429.7053911310305, "count": 351000, "is_parallel": true, "self": 9.491791716031855, "children": { "process_trajectory": { "total": 246.19190509699854, "count": 351000, "is_parallel": true, "self": 245.46168786999857, "children": { "RLTrainer._checkpoint": { "total": 0.7302172269999687, "count": 4, "is_parallel": true, "self": 0.7302172269999687 } } }, "_update_policy": { "total": 174.02169431800013, "count": 90, "is_parallel": true, "self": 45.05036746299771, "children": { "TorchPPOOptimizer.update": { "total": 128.97132685500242, "count": 4587, "is_parallel": true, "self": 128.97132685500242 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1268865999999207, "count": 1, "self": 0.0009127369999077928, "children": { "RLTrainer._checkpoint": { "total": 0.1259738630000129, "count": 1, "self": 0.1259738630000129 } } } } } } }