{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.4351891577243805, "min": 0.4124315679073334, "max": 2.8701202869415283, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4475.92041015625, "min": 4037.46240234375, "max": 29392.90234375, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.28770923614502, "min": 0.2245347946882248, "max": 14.431157112121582, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2928.98046875, "min": 43.559749603271484, "max": 2952.845703125, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0699265562830203, "min": 0.06112103356951824, "max": 0.0775976367634333, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3496327814151015, "min": 0.24448413427807297, "max": 0.3879881838171665, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1627186337522432, "min": 0.11146447093308193, "max": 0.26447473488309803, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.813593168761216, "min": 0.4458578837323277, "max": 1.2789767162472594, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000039e-07, "min": 7.032997656000039e-07, "max": 0.00029918820027059994, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000196e-06, "min": 3.5164988280000196e-06, "max": 0.0014885160038279998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.1997294, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.4029176, "max": 0.996172, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000067e-05, "min": 2.1696560000000067e-05, "max": 0.004986497059999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000034, "min": 0.00010848280000000034, "max": 0.024808982800000004, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.836363636363636, "min": 3.2045454545454546, "max": 28.59090909090909, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1531.0, "min": 141.0, "max": 1566.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.836363636363636, "min": 3.2045454545454546, "max": 28.59090909090909, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1531.0, "min": 141.0, "max": 1566.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691753275", "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": "1691758072" }, "total": 4797.353921215001, "count": 1, "self": 0.48705223700017086, "children": { "run_training.setup": { "total": 0.0430377640000188, "count": 1, "self": 0.0430377640000188 }, "TrainerController.start_learning": { "total": 4796.823831214, "count": 1, "self": 5.9265866639343585, "children": { "TrainerController._reset_env": { "total": 4.720287638999935, "count": 1, "self": 4.720287638999935 }, "TrainerController.advance": { "total": 4786.035077367066, "count": 181872, "self": 2.8701099820254967, "children": { "env_step": { "total": 4783.164967385041, "count": 181872, "self": 3493.4310696112893, "children": { "SubprocessEnvManager._take_step": { "total": 1286.7908276269527, "count": 181872, "self": 18.777313051831698, "children": { "TorchPolicy.evaluate": { "total": 1268.013514575121, "count": 181872, "self": 1268.013514575121 } } }, "workers": { "total": 2.9430701467985045, "count": 181872, "self": 0.0, "children": { "worker_root": { "total": 4781.1309507520855, "count": 181872, "is_parallel": true, "self": 2244.634284836039, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009122021000052882, "count": 1, "is_parallel": true, "self": 0.007517592999988665, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016044280000642175, "count": 10, "is_parallel": true, "self": 0.0016044280000642175 } } }, "UnityEnvironment.step": { "total": 0.07782980299998599, "count": 1, "is_parallel": true, "self": 0.0006065569999691434, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003981920000342143, "count": 1, "is_parallel": true, "self": 0.0003981920000342143 }, "communicator.exchange": { "total": 0.07463931899997078, "count": 1, "is_parallel": true, "self": 0.07463931899997078 }, "steps_from_proto": { "total": 0.002185735000011846, "count": 1, "is_parallel": true, "self": 0.0003915009998536334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017942340001582124, "count": 10, "is_parallel": true, "self": 0.0017942340001582124 } } } } } } }, "UnityEnvironment.step": { "total": 2536.4966659160464, "count": 181871, "is_parallel": true, "self": 107.16965771905052, "children": { "UnityEnvironment._generate_step_input": { "total": 53.56370950306939, "count": 181871, "is_parallel": true, "self": 53.56370950306939 }, "communicator.exchange": { "total": 2010.717184664041, "count": 181871, "is_parallel": true, "self": 2010.717184664041 }, "steps_from_proto": { "total": 365.0461140298853, "count": 181871, "is_parallel": true, "self": 67.54184858460121, "children": { "_process_rank_one_or_two_observation": { "total": 297.5042654452841, "count": 1818710, "is_parallel": true, "self": 297.5042654452841 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003264699998908327, "count": 1, "self": 0.0003264699998908327, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 4748.895687837884, "count": 4393645, "is_parallel": true, "self": 96.52607736498157, "children": { "process_trajectory": { "total": 2576.4395320578965, "count": 4393645, "is_parallel": true, "self": 2561.9673742028976, "children": { "RLTrainer._checkpoint": { "total": 14.472157854998727, "count": 40, "is_parallel": true, "self": 14.472157854998727 } } }, "_update_policy": { "total": 2075.9300784150055, "count": 909, "is_parallel": true, "self": 824.9928528110536, "children": { "TorchPPOOptimizer.update": { "total": 1250.937225603952, "count": 46347, "is_parallel": true, "self": 1250.937225603952 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14155307399960293, "count": 1, "self": 0.0009410039992872044, "children": { "RLTrainer._checkpoint": { "total": 0.14061207000031573, "count": 1, "self": 0.14061207000031573 } } } } } } }