{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9037067294120789, "min": 0.9037067294120789, "max": 2.8543758392333984, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8628.591796875, "min": 8628.591796875, "max": 29231.662109375, "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": 12.921146392822266, "min": 0.34712517261505127, "max": 13.001911163330078, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.62353515625, "min": 67.34228515625, "max": 2652.389892578125, "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": 0.07127353979269495, "min": 0.06261417612149914, "max": 0.07391044691779397, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2850941591707798, "min": 0.25045670448599655, "max": 0.36912612135761175, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2123601085634208, "min": 0.11241443117158306, "max": 0.29668478382860913, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8494404342536832, "min": 0.44965772468633225, "max": 1.4294627441787253, "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": 25.34090909090909, "min": 3.340909090909091, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 147.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 3.340909090909091, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 147.0, "max": 1417.0, "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": "1695551028", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1695551589" }, "total": 560.9850440560001, "count": 1, "self": 0.4859645700000783, "children": { "run_training.setup": { "total": 0.050706521999927645, "count": 1, "self": 0.050706521999927645 }, "TrainerController.start_learning": { "total": 560.4483729640001, "count": 1, "self": 0.7351394159948086, "children": { "TrainerController._reset_env": { "total": 5.026813476999905, "count": 1, "self": 5.026813476999905 }, "TrainerController.advance": { "total": 554.5396895760057, "count": 18201, "self": 0.39203106601598847, "children": { "env_step": { "total": 554.1476585099897, "count": 18201, "self": 406.35165445898383, "children": { "SubprocessEnvManager._take_step": { "total": 147.4285914780105, "count": 18201, "self": 2.15413106901633, "children": { "TorchPolicy.evaluate": { "total": 145.27446040899417, "count": 18201, "self": 145.27446040899417 } } }, "workers": { "total": 0.367412572995363, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 558.507853154011, "count": 18201, "is_parallel": true, "self": 257.394942924994, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007113126999911401, "count": 1, "is_parallel": true, "self": 0.005419284000026892, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016938429998845095, "count": 10, "is_parallel": true, "self": 0.0016938429998845095 } } }, "UnityEnvironment.step": { "total": 0.11251805500000955, "count": 1, "is_parallel": true, "self": 0.000698670000247148, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041927299980670796, "count": 1, "is_parallel": true, "self": 0.00041927299980670796 }, "communicator.exchange": { "total": 0.10786829999983638, "count": 1, "is_parallel": true, "self": 0.10786829999983638 }, "steps_from_proto": { "total": 0.0035318120001193165, "count": 1, "is_parallel": true, "self": 0.0015220120003505144, "children": { "_process_rank_one_or_two_observation": { "total": 0.002009799999768802, "count": 10, "is_parallel": true, "self": 0.002009799999768802 } } } } } } }, "UnityEnvironment.step": { "total": 301.11291022901696, "count": 18200, "is_parallel": true, "self": 12.57127503901279, "children": { "UnityEnvironment._generate_step_input": { "total": 6.316822294989379, "count": 18200, "is_parallel": true, "self": 6.316822294989379 }, "communicator.exchange": { "total": 238.5906759860004, "count": 18200, "is_parallel": true, "self": 238.5906759860004 }, "steps_from_proto": { "total": 43.63413690901439, "count": 18200, "is_parallel": true, "self": 8.64298720799502, "children": { "_process_rank_one_or_two_observation": { "total": 34.99114970101937, "count": 182000, "is_parallel": true, "self": 34.99114970101937 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.48719998884917e-05, "count": 1, "self": 8.48719998884917e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 550.1221630789721, "count": 519354, "is_parallel": true, "self": 12.259066761925851, "children": { "process_trajectory": { "total": 301.625182495045, "count": 519354, "is_parallel": true, "self": 300.1958866310449, "children": { "RLTrainer._checkpoint": { "total": 1.4292958640000961, "count": 4, "is_parallel": true, "self": 1.4292958640000961 } } }, "_update_policy": { "total": 236.23791382200125, "count": 90, "is_parallel": true, "self": 93.65433933400436, "children": { "TorchPPOOptimizer.update": { "total": 142.58357448799688, "count": 4584, "is_parallel": true, "self": 142.58357448799688 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14664562299981299, "count": 1, "self": 0.0010096279997924285, "children": { "RLTrainer._checkpoint": { "total": 0.14563599500002056, "count": 1, "self": 0.14563599500002056 } } } } } } }