{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0821439027786255, "min": 1.0821439027786255, "max": 2.8646936416625977, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10368.0205078125, "min": 10368.0205078125, "max": 29337.328125, "count": 40 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.131266593933105, "min": 0.4599519968032837, "max": 12.131266593933105, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2365.596923828125, "min": 89.2306900024414, "max": 2414.58447265625, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06497834889730666, "min": 0.06319415741446016, "max": 0.07435261581079376, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25991339558922666, "min": 0.25277662965784065, "max": 0.3670477070663051, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19505600287925964, "min": 0.1286619952925499, "max": 0.2551515409138565, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7802240115170386, "min": 0.5146479811701996, "max": 1.2757577045692825, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291906002698, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19730199999999998, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004865369800000001, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.0, "min": 3.772727272727273, "max": 24.381818181818183, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1056.0, "min": 166.0, "max": 1341.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.0, "min": 3.772727272727273, "max": 24.381818181818183, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1056.0, "min": 166.0, "max": 1341.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678644731", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678645222" }, "total": 490.7671269570001, "count": 1, "self": 0.43302493000021514, "children": { "run_training.setup": { "total": 0.1797794909999766, "count": 1, "self": 0.1797794909999766 }, "TrainerController.start_learning": { "total": 490.1543225359999, "count": 1, "self": 0.6180219950070978, "children": { "TrainerController._reset_env": { "total": 10.888456376000022, "count": 1, "self": 10.888456376000022 }, "TrainerController.advance": { "total": 478.5292816759928, "count": 18216, "self": 0.3118605890110757, "children": { "env_step": { "total": 478.21742108698174, "count": 18216, "self": 337.0039272349816, "children": { "SubprocessEnvManager._take_step": { "total": 140.76531941099256, "count": 18216, "self": 1.904945231995157, "children": { "TorchPolicy.evaluate": { "total": 138.8603741789974, "count": 18216, "self": 138.8603741789974 } } }, "workers": { "total": 0.44817444100760895, "count": 18216, "self": 0.0, "children": { "worker_root": { "total": 488.2552073989974, "count": 18216, "is_parallel": true, "self": 236.66358961999777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002789744999972754, "count": 1, "is_parallel": true, "self": 0.0007507049998594084, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020390400001133457, "count": 10, "is_parallel": true, "self": 0.0020390400001133457 } } }, "UnityEnvironment.step": { "total": 0.07656992500005799, "count": 1, "is_parallel": true, "self": 0.0006211400001348011, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040462200001911697, "count": 1, "is_parallel": true, "self": 0.00040462200001911697 }, "communicator.exchange": { "total": 0.06718655299994225, "count": 1, "is_parallel": true, "self": 0.06718655299994225 }, "steps_from_proto": { "total": 0.008357609999961824, "count": 1, "is_parallel": true, "self": 0.0004024520000029952, "children": { "_process_rank_one_or_two_observation": { "total": 0.007955157999958828, "count": 10, "is_parallel": true, "self": 0.007955157999958828 } } } } } } }, "UnityEnvironment.step": { "total": 251.59161777899965, "count": 18215, "is_parallel": true, "self": 9.792848131001847, "children": { "UnityEnvironment._generate_step_input": { "total": 5.176156897993906, "count": 18215, "is_parallel": true, "self": 5.176156897993906 }, "communicator.exchange": { "total": 204.3602397150055, "count": 18215, "is_parallel": true, "self": 204.3602397150055 }, "steps_from_proto": { "total": 32.262373034998404, "count": 18215, "is_parallel": true, "self": 6.53333437498236, "children": { "_process_rank_one_or_two_observation": { "total": 25.729038660016045, "count": 182150, "is_parallel": true, "self": 25.729038660016045 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001655300000038551, "count": 1, "self": 0.0001655300000038551, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 474.6668227181093, "count": 452101, "is_parallel": true, "self": 11.091373714068936, "children": { "process_trajectory": { "total": 265.95055973504043, "count": 452101, "is_parallel": true, "self": 264.4282893930407, "children": { "RLTrainer._checkpoint": { "total": 1.5222703419997288, "count": 4, "is_parallel": true, "self": 1.5222703419997288 } } }, "_update_policy": { "total": 197.62488926899994, "count": 90, "is_parallel": true, "self": 75.86693473801336, "children": { "TorchPPOOptimizer.update": { "total": 121.75795453098658, "count": 4581, "is_parallel": true, "self": 121.75795453098658 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11839695899993785, "count": 1, "self": 0.0009528099999442929, "children": { "RLTrainer._checkpoint": { "total": 0.11744414899999356, "count": 1, "self": 0.11744414899999356 } } } } } } }