{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8038665056228638, "min": 0.7955447435379028, "max": 2.82368803024292, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7639.947265625, "min": 7639.947265625, "max": 28824.20703125, "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": 12.968066215515137, "min": 0.4422927796840668, "max": 12.968066215515137, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2528.77294921875, "min": 85.80480194091797, "max": 2626.849365234375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.074644087231397, "min": 0.06056956412914373, "max": 0.074644087231397, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.298576348925588, "min": 0.25064241312622254, "max": 0.36150309034079936, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20727182672742536, "min": 0.13348645052196934, "max": 0.28937286050880656, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8290873069097014, "min": 0.5339458020878773, "max": 1.3663718270904879, "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": 25.59090909090909, "min": 4.159090909090909, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 183.0, "max": 1420.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 4.159090909090909, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 183.0, "max": 1420.0, "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": "1780997291", "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": "1780997766" }, "total": 474.1881094170001, "count": 1, "self": 0.4832112239998878, "children": { "run_training.setup": { "total": 0.026216507000071942, "count": 1, "self": 0.026216507000071942 }, "TrainerController.start_learning": { "total": 473.6786816860001, "count": 1, "self": 0.39097240503224384, "children": { "TrainerController._reset_env": { "total": 3.3123518679999506, "count": 1, "self": 3.3123518679999506 }, "TrainerController.advance": { "total": 469.889657136968, "count": 18192, "self": 0.4279755769616713, "children": { "env_step": { "total": 343.94777938199945, "count": 18192, "self": 268.94415064700934, "children": { "SubprocessEnvManager._take_step": { "total": 74.77526964298545, "count": 18192, "self": 1.289981957965665, "children": { "TorchPolicy.evaluate": { "total": 73.48528768501978, "count": 18192, "self": 73.48528768501978 } } }, "workers": { "total": 0.2283590920046663, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 471.7280313050005, "count": 18192, "is_parallel": true, "self": 235.47324615001276, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005016459999978906, "count": 1, "is_parallel": true, "self": 0.0037699279998832935, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012465320000956126, "count": 10, "is_parallel": true, "self": 0.0012465320000956126 } } }, "UnityEnvironment.step": { "total": 0.03924831099993753, "count": 1, "is_parallel": true, "self": 0.0005707109999093518, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041379100002814084, "count": 1, "is_parallel": true, "self": 0.00041379100002814084 }, "communicator.exchange": { "total": 0.036047112000005654, "count": 1, "is_parallel": true, "self": 0.036047112000005654 }, "steps_from_proto": { "total": 0.002216696999994383, "count": 1, "is_parallel": true, "self": 0.000397500999724798, "children": { "_process_rank_one_or_two_observation": { "total": 0.001819196000269585, "count": 10, "is_parallel": true, "self": 0.001819196000269585 } } } } } } }, "UnityEnvironment.step": { "total": 236.25478515498776, "count": 18191, "is_parallel": true, "self": 10.834087840954908, "children": { "UnityEnvironment._generate_step_input": { "total": 5.723279592016752, "count": 18191, "is_parallel": true, "self": 5.723279592016752 }, "communicator.exchange": { "total": 180.52094920102786, "count": 18191, "is_parallel": true, "self": 180.52094920102786 }, "steps_from_proto": { "total": 39.17646852098824, "count": 18191, "is_parallel": true, "self": 6.897358273917689, "children": { "_process_rank_one_or_two_observation": { "total": 32.27911024707055, "count": 181910, "is_parallel": true, "self": 32.27911024707055 } } } } } } } } } } }, "trainer_advance": { "total": 125.5139021780069, "count": 18192, "self": 0.4599650040106553, "children": { "process_trajectory": { "total": 28.1708023019969, "count": 18192, "self": 27.74404870399644, "children": { "RLTrainer._checkpoint": { "total": 0.42675359800045953, "count": 4, "self": 0.42675359800045953 } } }, "_update_policy": { "total": 96.88313487199935, "count": 90, "self": 39.6757778959975, "children": { "TorchPPOOptimizer.update": { "total": 57.20735697600185, "count": 4587, "self": 57.20735697600185 } } } } } } }, "trainer_threads": { "total": 1.4020001799508464e-06, "count": 1, "self": 1.4020001799508464e-06 }, "TrainerController._save_models": { "total": 0.08569887399971776, "count": 1, "self": 0.0008168989998011966, "children": { "RLTrainer._checkpoint": { "total": 0.08488197499991657, "count": 1, "self": 0.08488197499991657 } } } } } } }