{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.5011484622955322, "min": 2.5011484622955322, "max": 2.8680579662323, "count": 4 }, "SnowballTarget.Policy.Entropy.sum": { "value": 25614.26171875, "min": 25480.396484375, "max": 29371.78125, "count": 4 }, "SnowballTarget.Step.mean": { "value": 39984.0, "min": 9952.0, "max": 39984.0, "count": 4 }, "SnowballTarget.Step.sum": { "value": 39984.0, "min": 9952.0, "max": 39984.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 3.4007062911987305, "min": 0.4964136779308319, "max": 3.4007062911987305, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 697.144775390625, "min": 96.30425262451172, "max": 697.144775390625, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06724189642768846, "min": 0.06545925535354792, "max": 0.07198938031856704, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3362094821384423, "min": 0.2618370214141917, "max": 0.3435879141658969, "count": 4 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.26050749906137877, "min": 0.12958442741621506, "max": 0.26050749906137877, "count": 4 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.3025374953068938, "min": 0.5183377096648603, "max": 1.3025374953068938, "count": 4 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.000247332017556, "min": 0.000247332017556, "max": 0.000291882002706, "count": 4 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00123666008778, "min": 0.001048728050424, "max": 0.00138516003828, "count": 4 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.182444, "min": 0.182444, "max": 0.19729400000000002, "count": 4 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.91222, "min": 0.7495760000000001, "max": 0.96172, "count": 4 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0041239556000000005, "min": 0.0041239556000000005, "max": 0.0048649706, "count": 4 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.020619778000000002, "min": 0.017483842399999998, "max": 0.023089828, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 9.745454545454546, "min": 3.6818181818181817, "max": 9.745454545454546, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 536.0, "min": 162.0, "max": 536.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 9.745454545454546, "min": 3.6818181818181817, "max": 9.745454545454546, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 536.0, "min": 162.0, "max": 536.0, "count": 4 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679601307", "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": "0.31.0.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": "1679601420" }, "total": 113.13805195499998, "count": 1, "self": 0.5925590929999203, "children": { "run_training.setup": { "total": 0.14755938900003684, "count": 1, "self": 0.14755938900003684 }, "TrainerController.start_learning": { "total": 112.39793347300002, "count": 1, "self": 0.18703768699856482, "children": { "TrainerController._reset_env": { "total": 7.21208760799999, "count": 1, "self": 7.21208760799999 }, "TrainerController.advance": { "total": 104.74607768300149, "count": 3776, "self": 0.08626606600086006, "children": { "env_step": { "total": 104.65981161700063, "count": 3776, "self": 83.79722994100138, "children": { "SubprocessEnvManager._take_step": { "total": 20.777455623999174, "count": 3776, "self": 0.9765279589972238, "children": { "TorchPolicy.evaluate": { "total": 19.80092766500195, "count": 3776, "self": 19.80092766500195 } } }, "workers": { "total": 0.08512605200007783, "count": 3775, "self": 0.0, "children": { "worker_root": { "total": 111.79638906800318, "count": 3775, "is_parallel": true, "self": 53.29875949400298, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005979508999985228, "count": 1, "is_parallel": true, "self": 0.004350637000015922, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016288719999693058, "count": 10, "is_parallel": true, "self": 0.0016288719999693058 } } }, "UnityEnvironment.step": { "total": 0.03412332900001047, "count": 1, "is_parallel": true, "self": 0.0006725410000285592, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038394999995716717, "count": 1, "is_parallel": true, "self": 0.00038394999995716717 }, "communicator.exchange": { "total": 0.031292018000044663, "count": 1, "is_parallel": true, "self": 0.031292018000044663 }, "steps_from_proto": { "total": 0.0017748199999800818, "count": 1, "is_parallel": true, "self": 0.00038848000002644767, "children": { "_process_rank_one_or_two_observation": { "total": 0.001386339999953634, "count": 10, "is_parallel": true, "self": 0.001386339999953634 } } } } } } }, "UnityEnvironment.step": { "total": 58.4976295740002, "count": 3774, "is_parallel": true, "self": 2.232591015992739, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3561096210019628, "count": 3774, "is_parallel": true, "self": 1.3561096210019628 }, "communicator.exchange": { "total": 47.766040094003756, "count": 3774, "is_parallel": true, "self": 47.766040094003756 }, "steps_from_proto": { "total": 7.142888843001742, "count": 3774, "is_parallel": true, "self": 1.5731605450089319, "children": { "_process_rank_one_or_two_observation": { "total": 5.56972829799281, "count": 37740, "is_parallel": true, "self": 5.56972829799281 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.043999999543303e-05, "count": 1, "self": 5.043999999543303e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 104.00646663000742, "count": 107463, "is_parallel": true, "self": 2.2027032020147885, "children": { "process_trajectory": { "total": 58.48694914299256, "count": 107463, "is_parallel": true, "self": 58.48694914299256 }, "_update_policy": { "total": 43.31681428500008, "count": 18, "is_parallel": true, "self": 11.642654914999696, "children": { "TorchPPOOptimizer.update": { "total": 31.674159370000382, "count": 915, "is_parallel": true, "self": 31.674159370000382 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2526800549999848, "count": 1, "self": 0.0010210899999947287, "children": { "RLTrainer._checkpoint": { "total": 0.2516589649999901, "count": 1, "self": 0.2516589649999901 } } } } } } }