{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8028171062469482, "min": 0.8028171062469482, "max": 2.846391201019287, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7629.9736328125, "min": 7629.9736328125, "max": 29055.9609375, "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": 12.75141429901123, "min": 0.42579376697540283, "max": 12.75141429901123, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2486.52587890625, "min": 82.60398864746094, "max": 2548.625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06427153033676886, "min": 0.0629624819873225, "max": 0.07803287454161739, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2570861213470754, "min": 0.25382620294226843, "max": 0.36356944430564697, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19054623130781975, "min": 0.12412164439949408, "max": 0.2816580241801692, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.762184925231279, "min": 0.4964865775979763, "max": 1.3352376088207842, "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": 25.295454545454547, "min": 3.6136363636363638, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 159.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.6136363636363638, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 159.0, "max": 1387.0, "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": "1782583205", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1782583709" }, "total": 503.63994173200035, "count": 1, "self": 0.49611271100047816, "children": { "run_training.setup": { "total": 0.028218912999818713, "count": 1, "self": 0.028218912999818713 }, "TrainerController.start_learning": { "total": 503.11561010800006, "count": 1, "self": 0.4069587830090313, "children": { "TrainerController._reset_env": { "total": 3.69059586100002, "count": 1, "self": 3.69059586100002 }, "TrainerController.advance": { "total": 498.91772937599035, "count": 18192, "self": 0.4383548700488973, "children": { "env_step": { "total": 368.53757348097815, "count": 18192, "self": 288.5987389659722, "children": { "SubprocessEnvManager._take_step": { "total": 79.68725501603512, "count": 18192, "self": 1.4101212480127288, "children": { "TorchPolicy.evaluate": { "total": 78.2771337680224, "count": 18192, "self": 78.2771337680224 } } }, "workers": { "total": 0.2515794989708411, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 501.1886985620108, "count": 18192, "is_parallel": true, "self": 247.64818576899916, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004968490999999631, "count": 1, "is_parallel": true, "self": 0.0034471110011509154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015213799988487153, "count": 10, "is_parallel": true, "self": 0.0015213799988487153 } } }, "UnityEnvironment.step": { "total": 0.08229937400028575, "count": 1, "is_parallel": true, "self": 0.0007054170005176275, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004407169999467442, "count": 1, "is_parallel": true, "self": 0.0004407169999467442 }, "communicator.exchange": { "total": 0.07546053799978836, "count": 1, "is_parallel": true, "self": 0.07546053799978836 }, "steps_from_proto": { "total": 0.005692702000033023, "count": 1, "is_parallel": true, "self": 0.0004515240002547216, "children": { "_process_rank_one_or_two_observation": { "total": 0.0052411779997783015, "count": 10, "is_parallel": true, "self": 0.0052411779997783015 } } } } } } }, "UnityEnvironment.step": { "total": 253.54051279301166, "count": 18191, "is_parallel": true, "self": 11.382211088968688, "children": { "UnityEnvironment._generate_step_input": { "total": 6.153760651012817, "count": 18191, "is_parallel": true, "self": 6.153760651012817 }, "communicator.exchange": { "total": 193.50880566502155, "count": 18191, "is_parallel": true, "self": 193.50880566502155 }, "steps_from_proto": { "total": 42.4957353880086, "count": 18191, "is_parallel": true, "self": 7.2991782329604575, "children": { "_process_rank_one_or_two_observation": { "total": 35.19655715504814, "count": 181910, "is_parallel": true, "self": 35.19655715504814 } } } } } } } } } } }, "trainer_advance": { "total": 129.9418010249633, "count": 18192, "self": 0.5009886729885693, "children": { "process_trajectory": { "total": 27.20162467796945, "count": 18192, "self": 26.595803323968994, "children": { "RLTrainer._checkpoint": { "total": 0.6058213540004544, "count": 4, "self": 0.6058213540004544 } } }, "_update_policy": { "total": 102.23918767400528, "count": 90, "self": 41.58977326302556, "children": { "TorchPPOOptimizer.update": { "total": 60.649414410979716, "count": 4587, "self": 60.649414410979716 } } } } } } }, "trainer_threads": { "total": 9.880004654405639e-07, "count": 1, "self": 9.880004654405639e-07 }, "TrainerController._save_models": { "total": 0.10032510000019101, "count": 1, "self": 0.001195106000523083, "children": { "RLTrainer._checkpoint": { "total": 0.09912999399966793, "count": 1, "self": 0.09912999399966793 } } } } } } }