{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.627651333808899, "min": 1.627651333808899, "max": 2.866985321044922, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 16650.873046875, "min": 15977.548828125, "max": 29392.333984375, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.94714641571045, "min": 0.35663580894470215, "max": 8.94714641571045, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1825.2177734375, "min": 69.18734741210938, "max": 1825.2177734375, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06817418922500128, "min": 0.06074549209801726, "max": 0.07147828821690898, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3408709461250064, "min": 0.24298196839206904, "max": 0.3573914410845449, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2397519979991165, "min": 0.11029678730490416, "max": 0.2849704176004903, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1987599899955825, "min": 0.44118714921961666, "max": 1.4248520880024516, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 19.21818181818182, "min": 2.909090909090909, "max": 19.21818181818182, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1057.0, "min": 128.0, "max": 1057.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.21818181818182, "min": 2.909090909090909, "max": 19.21818181818182, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1057.0, "min": 128.0, "max": 1057.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679713845", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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 --force", "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": "1679714088" }, "total": 243.89199006800027, "count": 1, "self": 0.38471125300020503, "children": { "run_training.setup": { "total": 0.10892442599970309, "count": 1, "self": 0.10892442599970309 }, "TrainerController.start_learning": { "total": 243.39835438900036, "count": 1, "self": 0.33440892499993424, "children": { "TrainerController._reset_env": { "total": 7.067016918000263, "count": 1, "self": 7.067016918000263 }, "TrainerController.advance": { "total": 235.8580835040002, "count": 9134, "self": 0.15459857103405739, "children": { "env_step": { "total": 235.70348493296615, "count": 9134, "self": 170.62647063897202, "children": { "SubprocessEnvManager._take_step": { "total": 64.92798883497971, "count": 9134, "self": 1.0956969949688755, "children": { "TorchPolicy.evaluate": { "total": 63.83229184001084, "count": 9134, "self": 63.83229184001084 } } }, "workers": { "total": 0.14902545901441044, "count": 9134, "self": 0.0, "children": { "worker_root": { "total": 242.49072479397182, "count": 9134, "is_parallel": true, "self": 116.59553349297494, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002028880000125355, "count": 1, "is_parallel": true, "self": 0.0005723560002479644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014565239998773905, "count": 10, "is_parallel": true, "self": 0.0014565239998773905 } } }, "UnityEnvironment.step": { "total": 0.07259058999989065, "count": 1, "is_parallel": true, "self": 0.0006177609998303524, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048356299976148875, "count": 1, "is_parallel": true, "self": 0.00048356299976148875 }, "communicator.exchange": { "total": 0.06932247200029451, "count": 1, "is_parallel": true, "self": 0.06932247200029451 }, "steps_from_proto": { "total": 0.0021667940000043018, "count": 1, "is_parallel": true, "self": 0.0004544650000752881, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017123289999290137, "count": 10, "is_parallel": true, "self": 0.0017123289999290137 } } } } } } }, "UnityEnvironment.step": { "total": 125.89519130099688, "count": 9133, "is_parallel": true, "self": 4.836231269009659, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6928135770053814, "count": 9133, "is_parallel": true, "self": 2.6928135770053814 }, "communicator.exchange": { "total": 102.33023797397345, "count": 9133, "is_parallel": true, "self": 102.33023797397345 }, "steps_from_proto": { "total": 16.03590848100839, "count": 9133, "is_parallel": true, "self": 3.322913808951398, "children": { "_process_rank_one_or_two_observation": { "total": 12.712994672056993, "count": 91330, "is_parallel": true, "self": 12.712994672056993 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00033308499996564933, "count": 1, "self": 0.00033308499996564933, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 234.06776894705536, "count": 216508, "is_parallel": true, "self": 5.297274749152166, "children": { "process_trajectory": { "total": 131.55494170290467, "count": 216508, "is_parallel": true, "self": 130.77992980590443, "children": { "RLTrainer._checkpoint": { "total": 0.7750118970002404, "count": 2, "is_parallel": true, "self": 0.7750118970002404 } } }, "_update_policy": { "total": 97.21555249499852, "count": 45, "is_parallel": true, "self": 34.20578441999487, "children": { "TorchPPOOptimizer.update": { "total": 63.00976807500365, "count": 2289, "is_parallel": true, "self": 63.00976807500365 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13851195699999153, "count": 1, "self": 0.0012003159999949276, "children": { "RLTrainer._checkpoint": { "total": 0.1373116409999966, "count": 1, "self": 0.1373116409999966 } } } } } } }