{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9390293955802917, "min": 0.9390293955802917, "max": 2.8288023471832275, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8924.53515625, "min": 8924.53515625, "max": 28876.4140625, "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": 12.880203247070312, "min": 0.35900792479515076, "max": 12.880203247070312, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.6396484375, "min": 69.64753723144531, "max": 2596.8466796875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07122520180753639, "min": 0.06074552852620471, "max": 0.07520749366696121, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28490080723014555, "min": 0.24298211410481885, "max": 0.37603746833480606, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1892197706243571, "min": 0.13166235872845658, "max": 0.2675151028031228, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7568790824974284, "min": 0.5266494349138263, "max": 1.2984753601691301, "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.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.Environment.CumulativeReward.mean": { "value": 25.477272727272727, "min": 3.3636363636363638, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 148.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.3636363636363638, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 148.0, "max": 1369.0, "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": "1785724809", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/miniconda/envs/myenv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.13.0+cu130", "numpy_version": "1.23.5", "end_time_seconds": "1785725444" }, "total": 634.6280765720003, "count": 1, "self": 1.096786787000383, "children": { "run_training.setup": { "total": 0.040003105999858235, "count": 1, "self": 0.040003105999858235 }, "TrainerController.start_learning": { "total": 633.491286679, "count": 1, "self": 0.6607983460380638, "children": { "TrainerController._reset_env": { "total": 3.6621044749999783, "count": 1, "self": 3.6621044749999783 }, "TrainerController.advance": { "total": 626.2677713489629, "count": 18192, "self": 0.722655182876224, "children": { "env_step": { "total": 443.7718769649946, "count": 18192, "self": 386.45872963108104, "children": { "SubprocessEnvManager._take_step": { "total": 56.891657104968544, "count": 18192, "self": 2.20455743392813, "children": { "TorchPolicy.evaluate": { "total": 54.687099671040414, "count": 18192, "self": 54.687099671040414 } } }, "workers": { "total": 0.42149022894500376, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 625.1903136900146, "count": 18192, "is_parallel": true, "self": 290.31160797404027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004526573000475764, "count": 1, "is_parallel": true, "self": 0.0017487720015196828, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027778009989560815, "count": 10, "is_parallel": true, "self": 0.0027778009989560815 } } }, "UnityEnvironment.step": { "total": 0.09131382900068274, "count": 1, "is_parallel": true, "self": 0.0007159670003602514, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039540000034321565, "count": 1, "is_parallel": true, "self": 0.00039540000034321565 }, "communicator.exchange": { "total": 0.08482526199986751, "count": 1, "is_parallel": true, "self": 0.08482526199986751 }, "steps_from_proto": { "total": 0.00537720000011177, "count": 1, "is_parallel": true, "self": 0.0004208820009807823, "children": { "_process_rank_one_or_two_observation": { "total": 0.004956317999130988, "count": 10, "is_parallel": true, "self": 0.004956317999130988 } } } } } } }, "UnityEnvironment.step": { "total": 334.8787057159743, "count": 18191, "is_parallel": true, "self": 15.692023226034507, "children": { "UnityEnvironment._generate_step_input": { "total": 8.288316903948726, "count": 18191, "is_parallel": true, "self": 8.288316903948726 }, "communicator.exchange": { "total": 257.6431427219386, "count": 18191, "is_parallel": true, "self": 257.6431427219386 }, "steps_from_proto": { "total": 53.255222864052485, "count": 18191, "is_parallel": true, "self": 9.739905713047847, "children": { "_process_rank_one_or_two_observation": { "total": 43.51531715100464, "count": 181910, "is_parallel": true, "self": 43.51531715100464 } } } } } } } } } } }, "trainer_advance": { "total": 181.7732392010921, "count": 18192, "self": 0.906415834055224, "children": { "process_trajectory": { "total": 48.10940540203137, "count": 18192, "self": 34.10447697403106, "children": { "RLTrainer._checkpoint": { "total": 14.004928428000312, "count": 4, "self": 14.004928428000312 } } }, "_update_policy": { "total": 132.75741796500552, "count": 90, "self": 49.3012418659946, "children": { "TorchPPOOptimizer.update": { "total": 83.45617609901092, "count": 4587, "self": 83.45617609901092 } } } } } } }, "trainer_threads": { "total": 1.038999471347779e-06, "count": 1, "self": 1.038999471347779e-06 }, "TrainerController._save_models": { "total": 2.9006114699996033, "count": 1, "self": 0.0010145119995286223, "children": { "RLTrainer._checkpoint": { "total": 2.8995969580000747, "count": 1, "self": 2.8995969580000747 } } } } } } }