{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9615947604179382, "min": 0.9615947604179382, "max": 2.854032278060913, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9181.306640625, "min": 9181.306640625, "max": 29165.35546875, "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": 13.072260856628418, "min": 0.42489057779312134, "max": 13.072260856628418, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2549.0908203125, "min": 82.42877197265625, "max": 2639.304931640625, "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": 0.07093930961256024, "min": 0.06181186505572815, "max": 0.0784609031178144, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.283757238450241, "min": 0.2472474602229126, "max": 0.36732903069716094, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18429326879627567, "min": 0.1151179762365406, "max": 0.2690799196122908, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7371730751851027, "min": 0.4604719049461624, "max": 1.3234889688445073, "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": 3.2954545454545454, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 145.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.2954545454545454, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 145.0, "max": 1428.0, "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": "1686142092", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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=SnowballTarget5 --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": "1686142537" }, "total": 445.28674499400006, "count": 1, "self": 0.3843044060000693, "children": { "run_training.setup": { "total": 0.041821798000000854, "count": 1, "self": 0.041821798000000854 }, "TrainerController.start_learning": { "total": 444.86061879, "count": 1, "self": 0.492975444991373, "children": { "TrainerController._reset_env": { "total": 3.6923171839999895, "count": 1, "self": 3.6923171839999895 }, "TrainerController.advance": { "total": 440.54472994600866, "count": 18200, "self": 0.2514475730195045, "children": { "env_step": { "total": 440.29328237298915, "count": 18200, "self": 321.830055681983, "children": { "SubprocessEnvManager._take_step": { "total": 118.21480352700297, "count": 18200, "self": 1.6935270280064287, "children": { "TorchPolicy.evaluate": { "total": 116.52127649899654, "count": 18200, "self": 116.52127649899654 } } }, "workers": { "total": 0.24842316400315667, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 443.3583309920014, "count": 18200, "is_parallel": true, "self": 208.72547955499863, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00505102100004251, "count": 1, "is_parallel": true, "self": 0.003518474000088645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015325469999538655, "count": 10, "is_parallel": true, "self": 0.0015325469999538655 } } }, "UnityEnvironment.step": { "total": 0.046565633999989586, "count": 1, "is_parallel": true, "self": 0.0005712970000217865, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039126599995142897, "count": 1, "is_parallel": true, "self": 0.00039126599995142897 }, "communicator.exchange": { "total": 0.04358782000002748, "count": 1, "is_parallel": true, "self": 0.04358782000002748 }, "steps_from_proto": { "total": 0.0020152509999888935, "count": 1, "is_parallel": true, "self": 0.0003608570000324107, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016543939999564827, "count": 10, "is_parallel": true, "self": 0.0016543939999564827 } } } } } } }, "UnityEnvironment.step": { "total": 234.63285143700278, "count": 18199, "is_parallel": true, "self": 9.896508060995416, "children": { "UnityEnvironment._generate_step_input": { "total": 5.040496504006114, "count": 18199, "is_parallel": true, "self": 5.040496504006114 }, "communicator.exchange": { "total": 186.8261358899968, "count": 18199, "is_parallel": true, "self": 186.8261358899968 }, "steps_from_proto": { "total": 32.86971098200445, "count": 18199, "is_parallel": true, "self": 5.920786333009801, "children": { "_process_rank_one_or_two_observation": { "total": 26.948924648994648, "count": 181990, "is_parallel": true, "self": 26.948924648994648 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014019599996117904, "count": 1, "self": 0.00014019599996117904, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 437.21345004301253, "count": 414103, "is_parallel": true, "self": 9.147673965010483, "children": { "process_trajectory": { "total": 239.1465029810018, "count": 414103, "is_parallel": true, "self": 237.9893085910017, "children": { "RLTrainer._checkpoint": { "total": 1.157194390000086, "count": 4, "is_parallel": true, "self": 1.157194390000086 } } }, "_update_policy": { "total": 188.91927309700026, "count": 90, "is_parallel": true, "self": 73.1314715419989, "children": { "TorchPPOOptimizer.update": { "total": 115.78780155500135, "count": 4587, "is_parallel": true, "self": 115.78780155500135 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13045601900000747, "count": 1, "self": 0.0008208550000290415, "children": { "RLTrainer._checkpoint": { "total": 0.12963516399997843, "count": 1, "self": 0.12963516399997843 } } } } } } }