{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9211534261703491, "min": 0.9194540977478027, "max": 2.866178274154663, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8795.1728515625, "min": 8795.1728515625, "max": 29384.05859375, "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": 12.956098556518555, "min": 0.41700127720832825, "max": 12.956098556518555, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.439208984375, "min": 80.89824676513672, "max": 2629.647705078125, "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": 0.06775881698477887, "min": 0.06029719133862184, "max": 0.07652578370870484, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2710352679391155, "min": 0.25079864891949016, "max": 0.3826289185435242, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19346547155987984, "min": 0.1284247581029822, "max": 0.27612554742132916, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7738618862395193, "min": 0.5136990324119288, "max": 1.3389549384112742, "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": 25.477272727272727, "min": 3.590909090909091, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 158.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.590909090909091, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 158.0, "max": 1400.0, "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": "1673497510", "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": "1673497946" }, "total": 435.5332801509999, "count": 1, "self": 0.3872294119997832, "children": { "run_training.setup": { "total": 0.10752395700001216, "count": 1, "self": 0.10752395700001216 }, "TrainerController.start_learning": { "total": 435.0385267820001, "count": 1, "self": 0.48670914199669824, "children": { "TrainerController._reset_env": { "total": 6.793657329000098, "count": 1, "self": 6.793657329000098 }, "TrainerController.advance": { "total": 427.6393242900034, "count": 18201, "self": 0.25507269101422025, "children": { "env_step": { "total": 427.3842515989892, "count": 18201, "self": 278.96255065199784, "children": { "SubprocessEnvManager._take_step": { "total": 148.150402945991, "count": 18201, "self": 1.4125824319972935, "children": { "TorchPolicy.evaluate": { "total": 146.7378205139937, "count": 18201, "self": 32.75158024596601, "children": { "TorchPolicy.sample_actions": { "total": 113.9862402680277, "count": 18201, "self": 113.9862402680277 } } } } }, "workers": { "total": 0.2712980010003321, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 433.7277120690063, "count": 18201, "is_parallel": true, "self": 210.42711466099206, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0063286339999422125, "count": 1, "is_parallel": true, "self": 0.0038391939998518865, "children": { "_process_rank_one_or_two_observation": { "total": 0.002489440000090326, "count": 10, "is_parallel": true, "self": 0.002489440000090326 } } }, "UnityEnvironment.step": { "total": 0.045894681000049786, "count": 1, "is_parallel": true, "self": 0.0005567340000425247, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003044780000891478, "count": 1, "is_parallel": true, "self": 0.0003044780000891478 }, "communicator.exchange": { "total": 0.043031254999959856, "count": 1, "is_parallel": true, "self": 0.043031254999959856 }, "steps_from_proto": { "total": 0.0020022139999582578, "count": 1, "is_parallel": true, "self": 0.0004498579997971319, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015523560001611258, "count": 10, "is_parallel": true, "self": 0.0015523560001611258 } } } } } } }, "UnityEnvironment.step": { "total": 223.30059740801426, "count": 18200, "is_parallel": true, "self": 8.536151572002609, "children": { "UnityEnvironment._generate_step_input": { "total": 5.157866999005137, "count": 18200, "is_parallel": true, "self": 5.157866999005137 }, "communicator.exchange": { "total": 177.85293807099822, "count": 18200, "is_parallel": true, "self": 177.85293807099822 }, "steps_from_proto": { "total": 31.75364076600829, "count": 18200, "is_parallel": true, "self": 6.811847479973267, "children": { "_process_rank_one_or_two_observation": { "total": 24.941793286035022, "count": 182000, "is_parallel": true, "self": 24.941793286035022 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.371499994704209e-05, "count": 1, "self": 4.371499994704209e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 424.6396007080051, "count": 338466, "is_parallel": true, "self": 9.280109640051592, "children": { "process_trajectory": { "total": 242.91460602195468, "count": 338466, "is_parallel": true, "self": 241.66445724895482, "children": { "RLTrainer._checkpoint": { "total": 1.2501487729998644, "count": 4, "is_parallel": true, "self": 1.2501487729998644 } } }, "_update_policy": { "total": 172.44488504599883, "count": 90, "is_parallel": true, "self": 44.67130850300293, "children": { "TorchPPOOptimizer.update": { "total": 127.7735765429959, "count": 4584, "is_parallel": true, "self": 127.7735765429959 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11879230599993207, "count": 1, "self": 0.0008886179998626176, "children": { "RLTrainer._checkpoint": { "total": 0.11790368800006945, "count": 1, "self": 0.11790368800006945 } } } } } } }