{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.902929961681366, "min": 0.902929961681366, "max": 2.8705010414123535, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8660.904296875, "min": 8660.904296875, "max": 29491.52734375, "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": 12.647385597229004, "min": 0.4411809742450714, "max": 12.647385597229004, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2466.240234375, "min": 85.589111328125, "max": 2543.10498046875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06782857057131716, "min": 0.06142537183055253, "max": 0.07368704345126924, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27131428228526866, "min": 0.24570148732221012, "max": 0.3684352172563462, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19874347224101133, "min": 0.11972915398084796, "max": 0.29159508528662664, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7949738889640453, "min": 0.47891661592339185, "max": 1.4579754264331333, "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": 25.0, "min": 3.1363636363636362, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 138.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.1363636363636362, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 138.0, "max": 1380.0, "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": "1673436123", "python_version": "3.8.9 (default, Jan 11 2023, 11:43:45) \n[GCC 8.5.0 20210514 (Red Hat 8.5.0-10)]", "command_line_arguments": "/home/marco/.virtualenvs/ml38/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.2+cu111", "numpy_version": "1.23.5", "end_time_seconds": "1673436461" }, "total": 338.0174554719997, "count": 1, "self": 0.524084843986202, "children": { "run_training.setup": { "total": 0.04953831300372258, "count": 1, "self": 0.04953831300372258 }, "TrainerController.start_learning": { "total": 337.4438323150098, "count": 1, "self": 0.4101792084693443, "children": { "TrainerController._reset_env": { "total": 12.883214303990826, "count": 1, "self": 12.883214303990826 }, "TrainerController.advance": { "total": 323.95672174557694, "count": 18214, "self": 0.20356133324094117, "children": { "env_step": { "total": 323.753160412336, "count": 18214, "self": 224.95255801221356, "children": { "SubprocessEnvManager._take_step": { "total": 98.60502452906803, "count": 18214, "self": 1.0979576910322066, "children": { "TorchPolicy.evaluate": { "total": 97.50706683803583, "count": 18214, "self": 15.703851092344848, "children": { "TorchPolicy.sample_actions": { "total": 81.80321574569098, "count": 18214, "self": 81.80321574569098 } } } } }, "workers": { "total": 0.19557787105441093, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 336.6936793025525, "count": 18214, "is_parallel": true, "self": 175.1665499197843, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018088739889208227, "count": 1, "is_parallel": true, "self": 0.0005538649566005915, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012550090323202312, "count": 10, "is_parallel": true, "self": 0.0012550090323202312 } } }, "UnityEnvironment.step": { "total": 0.02659904901520349, "count": 1, "is_parallel": true, "self": 0.0005889430176466703, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003693399776238948, "count": 1, "is_parallel": true, "self": 0.0003693399776238948 }, "communicator.exchange": { "total": 0.023675169999478385, "count": 1, "is_parallel": true, "self": 0.023675169999478385 }, "steps_from_proto": { "total": 0.001965596020454541, "count": 1, "is_parallel": true, "self": 0.00047118403017520905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014944119902793318, "count": 10, "is_parallel": true, "self": 0.0014944119902793318 } } } } } } }, "UnityEnvironment.step": { "total": 161.52712938276818, "count": 18213, "is_parallel": true, "self": 5.903481859480962, "children": { "UnityEnvironment._generate_step_input": { "total": 3.494265632616589, "count": 18213, "is_parallel": true, "self": 3.494265632616589 }, "communicator.exchange": { "total": 132.5240608890017, "count": 18213, "is_parallel": true, "self": 132.5240608890017 }, "steps_from_proto": { "total": 19.605321001668926, "count": 18213, "is_parallel": true, "self": 4.270388929842738, "children": { "_process_rank_one_or_two_observation": { "total": 15.334932071826188, "count": 182130, "is_parallel": true, "self": 15.334932071826188 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013516098260879517, "count": 1, "self": 0.00013516098260879517, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 323.66082205981365, "count": 164282, "is_parallel": true, "self": 1.704489472846035, "children": { "process_trajectory": { "total": 183.99937965584104, "count": 164282, "is_parallel": true, "self": 182.9695367628301, "children": { "RLTrainer._checkpoint": { "total": 1.0298428930109367, "count": 4, "is_parallel": true, "self": 1.0298428930109367 } } }, "_update_policy": { "total": 137.95695293112658, "count": 90, "is_parallel": true, "self": 37.398417749325745, "children": { "TorchPPOOptimizer.update": { "total": 100.55853518180083, "count": 4587, "is_parallel": true, "self": 100.55853518180083 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19358189599006437, "count": 1, "self": 0.00861429498763755, "children": { "RLTrainer._checkpoint": { "total": 0.18496760100242682, "count": 1, "self": 0.18496760100242682 } } } } } } }