{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9909581542015076, "min": 0.9909581542015076, "max": 2.8684535026550293, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9483.4697265625, "min": 9483.4697265625, "max": 29407.384765625, "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": 12.518369674682617, "min": 0.26601922512054443, "max": 12.518369674682617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2441.08203125, "min": 51.607730865478516, "max": 2517.97412109375, "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": 0.10222930409751521, "min": 0.08738147163542938, "max": 0.10233647466549312, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.40891721639006084, "min": 0.3495258865417175, "max": 0.5029112779110637, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1844092722178674, "min": 0.1193308531214271, "max": 0.26902768661578497, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7376370888714696, "min": 0.4773234124857084, "max": 1.3451384330789249, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.90909090909091, "min": 3.4318181818181817, "max": 24.963636363636365, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1096.0, "min": 151.0, "max": 1373.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.90909090909091, "min": 3.4318181818181817, "max": 24.963636363636365, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1096.0, "min": 151.0, "max": 1373.0, "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": "1687100426", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1687101028" }, "total": 602.098734662, "count": 1, "self": 0.48933148799994797, "children": { "run_training.setup": { "total": 0.05898093600001175, "count": 1, "self": 0.05898093600001175 }, "TrainerController.start_learning": { "total": 601.550422238, "count": 1, "self": 0.8165088700022807, "children": { "TrainerController._reset_env": { "total": 2.0502622889999884, "count": 1, "self": 2.0502622889999884 }, "TrainerController.advance": { "total": 598.5363873509976, "count": 18203, "self": 0.3818270439994649, "children": { "env_step": { "total": 598.1545603069982, "count": 18203, "self": 501.87054667900895, "children": { "SubprocessEnvManager._take_step": { "total": 95.89912197800311, "count": 18203, "self": 2.3019919740012256, "children": { "TorchPolicy.evaluate": { "total": 93.59713000400188, "count": 18203, "self": 93.59713000400188 } } }, "workers": { "total": 0.38489164998611614, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 599.2563216020079, "count": 18203, "is_parallel": true, "self": 279.33058643399, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008492684999964695, "count": 1, "is_parallel": true, "self": 0.005552001999944878, "children": { "_process_rank_one_or_two_observation": { "total": 0.002940683000019817, "count": 10, "is_parallel": true, "self": 0.002940683000019817 } } }, "UnityEnvironment.step": { "total": 0.07938626200007093, "count": 1, "is_parallel": true, "self": 0.0007645619999721021, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000495796999985032, "count": 1, "is_parallel": true, "self": 0.000495796999985032 }, "communicator.exchange": { "total": 0.07563837200007129, "count": 1, "is_parallel": true, "self": 0.07563837200007129 }, "steps_from_proto": { "total": 0.002487531000042509, "count": 1, "is_parallel": true, "self": 0.00041877700004988583, "children": { "_process_rank_one_or_two_observation": { "total": 0.002068753999992623, "count": 10, "is_parallel": true, "self": 0.002068753999992623 } } } } } } }, "UnityEnvironment.step": { "total": 319.9257351680179, "count": 18202, "is_parallel": true, "self": 13.631258882017391, "children": { "UnityEnvironment._generate_step_input": { "total": 7.098320055989689, "count": 18202, "is_parallel": true, "self": 7.098320055989689 }, "communicator.exchange": { "total": 253.50671271201156, "count": 18202, "is_parallel": true, "self": 253.50671271201156 }, "steps_from_proto": { "total": 45.68944351799928, "count": 18202, "is_parallel": true, "self": 8.98965067701647, "children": { "_process_rank_one_or_two_observation": { "total": 36.69979284098281, "count": 182020, "is_parallel": true, "self": 36.69979284098281 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001509759999862581, "count": 1, "self": 0.0001509759999862581, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 594.0146100580577, "count": 550625, "is_parallel": true, "self": 12.58996557615319, "children": { "process_trajectory": { "total": 302.8737572729043, "count": 550625, "is_parallel": true, "self": 296.152180942904, "children": { "RLTrainer._checkpoint": { "total": 6.721576330000289, "count": 20, "is_parallel": true, "self": 6.721576330000289 } } }, "_update_policy": { "total": 278.55088720900017, "count": 90, "is_parallel": true, "self": 80.87238860700847, "children": { "TorchPPOOptimizer.update": { "total": 197.6784986019917, "count": 9177, "is_parallel": true, "self": 197.6784986019917 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14711275200011187, "count": 1, "self": 0.0009958380001080513, "children": { "RLTrainer._checkpoint": { "total": 0.14611691400000382, "count": 1, "self": 0.14611691400000382 } } } } } } }