{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9045253992080688, "min": 0.9045253992080688, "max": 2.8672192096710205, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8686.1572265625, "min": 8686.1572265625, "max": 29363.19140625, "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": 12.772157669067383, "min": 0.2776370942592621, "max": 12.772157669067383, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2490.57080078125, "min": 53.861595153808594, "max": 2600.072509765625, "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": 0.06647583772998997, "min": 0.06389640538828625, "max": 0.07507504334181944, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26590335091995987, "min": 0.255585621553145, "max": 0.37414226971247677, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2055528931611893, "min": 0.0970677543789897, "max": 0.27923092696012236, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8222115726447572, "min": 0.3882710175159588, "max": 1.3961546348006117, "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": 24.431818181818183, "min": 2.75, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1075.0, "min": 121.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.431818181818183, "min": 2.75, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1075.0, "min": 121.0, "max": 1402.0, "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": "1676072193", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676072662" }, "total": 469.41777469, "count": 1, "self": 0.40108790099992575, "children": { "run_training.setup": { "total": 0.10661017500001435, "count": 1, "self": 0.10661017500001435 }, "TrainerController.start_learning": { "total": 468.91007661400005, "count": 1, "self": 0.5297069340096527, "children": { "TrainerController._reset_env": { "total": 9.824389274999987, "count": 1, "self": 9.824389274999987 }, "TrainerController.advance": { "total": 458.43677177899036, "count": 18221, "self": 0.27950087600208917, "children": { "env_step": { "total": 458.1572709029883, "count": 18221, "self": 312.226477230991, "children": { "SubprocessEnvManager._take_step": { "total": 145.662369879003, "count": 18221, "self": 1.4807670370026926, "children": { "TorchPolicy.evaluate": { "total": 144.1816028420003, "count": 18221, "self": 30.886107652999783, "children": { "TorchPolicy.sample_actions": { "total": 113.29549518900052, "count": 18221, "self": 113.29549518900052 } } } } }, "workers": { "total": 0.26842379299426966, "count": 18221, "self": 0.0, "children": { "worker_root": { "total": 467.3613096459916, "count": 18221, "is_parallel": true, "self": 227.63231964700316, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006330363000017769, "count": 1, "is_parallel": true, "self": 0.003813681999986329, "children": { "_process_rank_one_or_two_observation": { "total": 0.00251668100003144, "count": 10, "is_parallel": true, "self": 0.00251668100003144 } } }, "UnityEnvironment.step": { "total": 0.03735725500001763, "count": 1, "is_parallel": true, "self": 0.0006118020000371871, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000348234999989927, "count": 1, "is_parallel": true, "self": 0.000348234999989927 }, "communicator.exchange": { "total": 0.034282356999995045, "count": 1, "is_parallel": true, "self": 0.034282356999995045 }, "steps_from_proto": { "total": 0.0021148609999954715, "count": 1, "is_parallel": true, "self": 0.00048107299994626374, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016337880000492078, "count": 10, "is_parallel": true, "self": 0.0016337880000492078 } } } } } } }, "UnityEnvironment.step": { "total": 239.72898999898842, "count": 18220, "is_parallel": true, "self": 9.622059143977253, "children": { "UnityEnvironment._generate_step_input": { "total": 5.404850268005816, "count": 18220, "is_parallel": true, "self": 5.404850268005816 }, "communicator.exchange": { "total": 192.0055916730011, "count": 18220, "is_parallel": true, "self": 192.0055916730011 }, "steps_from_proto": { "total": 32.69648891400425, "count": 18220, "is_parallel": true, "self": 7.030509899981382, "children": { "_process_rank_one_or_two_observation": { "total": 25.665979014022867, "count": 182200, "is_parallel": true, "self": 25.665979014022867 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014753999994354672, "count": 1, "self": 0.00014753999994354672, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.93195155905175, "count": 406646, "is_parallel": true, "self": 10.458612185076845, "children": { "process_trajectory": { "total": 260.57414187197475, "count": 406646, "is_parallel": true, "self": 259.0683344309749, "children": { "RLTrainer._checkpoint": { "total": 1.5058074409998312, "count": 4, "is_parallel": true, "self": 1.5058074409998312 } } }, "_update_policy": { "total": 183.89919750200016, "count": 90, "is_parallel": true, "self": 63.212882693006634, "children": { "TorchPPOOptimizer.update": { "total": 120.68631480899353, "count": 4587, "is_parallel": true, "self": 120.68631480899353 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11906108600010157, "count": 1, "self": 0.000977393000084703, "children": { "RLTrainer._checkpoint": { "total": 0.11808369300001686, "count": 1, "self": 0.11808369300001686 } } } } } } }