{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8495714068412781, "min": 0.8382876515388489, "max": 2.840803384780884, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8074.32666015625, "min": 8074.32666015625, "max": 28998.921875, "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": 11.936359405517578, "min": 0.41909220814704895, "max": 11.936359405517578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2327.590087890625, "min": 81.30388641357422, "max": 2417.0166015625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06430333447197507, "min": 0.062251936447936196, "max": 0.07297009367874696, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2572133378879003, "min": 0.24900774579174478, "max": 0.3616254634118876, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18230735506935447, "min": 0.12281040227104563, "max": 0.28941110806430087, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7292294202774179, "min": 0.4912416090841825, "max": 1.2659057180086772, "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": 23.5, "min": 3.1818181818181817, "max": 23.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1034.0, "min": 140.0, "max": 1269.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.5, "min": 3.1818181818181817, "max": 23.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1034.0, "min": 140.0, "max": 1269.0, "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": "1774023652", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/lib/python3.10/site-packages/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume", "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": "1774024234" }, "total": 581.2938196499999, "count": 1, "self": 0.5975213299989264, "children": { "run_training.setup": { "total": 0.03937732800113736, "count": 1, "self": 0.03937732800113736 }, "TrainerController.start_learning": { "total": 580.6569209919999, "count": 1, "self": 0.5937159442346456, "children": { "TrainerController._reset_env": { "total": 3.91410201600047, "count": 1, "self": 3.91410201600047 }, "TrainerController.advance": { "total": 576.0684279127636, "count": 18192, "self": 0.6096275984818931, "children": { "env_step": { "total": 415.99566535015583, "count": 18192, "self": 362.4178563521946, "children": { "SubprocessEnvManager._take_step": { "total": 53.18150409413647, "count": 18192, "self": 1.9385799061838043, "children": { "TorchPolicy.evaluate": { "total": 51.24292418795267, "count": 18192, "self": 51.24292418795267 } } }, "workers": { "total": 0.39630490382478456, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 577.6514376129089, "count": 18192, "is_parallel": true, "self": 263.7280528768497, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0052026610010216245, "count": 1, "is_parallel": true, "self": 0.0035396950006543193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016629660003673052, "count": 10, "is_parallel": true, "self": 0.0016629660003673052 } } }, "UnityEnvironment.step": { "total": 0.05443938700045692, "count": 1, "is_parallel": true, "self": 0.0008351750002475455, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005071969990240177, "count": 1, "is_parallel": true, "self": 0.0005071969990240177 }, "communicator.exchange": { "total": 0.050434909000614425, "count": 1, "is_parallel": true, "self": 0.050434909000614425 }, "steps_from_proto": { "total": 0.0026621060005709296, "count": 1, "is_parallel": true, "self": 0.0008840300015435787, "children": { "_process_rank_one_or_two_observation": { "total": 0.001778075999027351, "count": 10, "is_parallel": true, "self": 0.001778075999027351 } } } } } } }, "UnityEnvironment.step": { "total": 313.92338473605923, "count": 18191, "is_parallel": true, "self": 14.182706522004082, "children": { "UnityEnvironment._generate_step_input": { "total": 7.99724836994028, "count": 18191, "is_parallel": true, "self": 7.99724836994028 }, "communicator.exchange": { "total": 242.18439552495875, "count": 18191, "is_parallel": true, "self": 242.18439552495875 }, "steps_from_proto": { "total": 49.559034319156126, "count": 18191, "is_parallel": true, "self": 8.762736314234644, "children": { "_process_rank_one_or_two_observation": { "total": 40.79629800492148, "count": 181910, "is_parallel": true, "self": 40.79629800492148 } } } } } } } } } } }, "trainer_advance": { "total": 159.46313496412586, "count": 18192, "self": 0.786757071975444, "children": { "process_trajectory": { "total": 30.328034483140073, "count": 18192, "self": 29.863303967140382, "children": { "RLTrainer._checkpoint": { "total": 0.4647305159996904, "count": 4, "self": 0.4647305159996904 } } }, "_update_policy": { "total": 128.34834340901034, "count": 90, "self": 49.59340976003659, "children": { "TorchPPOOptimizer.update": { "total": 78.75493364897375, "count": 4587, "self": 78.75493364897375 } } } } } } }, "trainer_threads": { "total": 1.0690000635804608e-06, "count": 1, "self": 1.0690000635804608e-06 }, "TrainerController._save_models": { "total": 0.08067405000110739, "count": 1, "self": 0.0011322850023134379, "children": { "RLTrainer._checkpoint": { "total": 0.07954176499879395, "count": 1, "self": 0.07954176499879395 } } } } } } }