{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0011041164398193, "min": 0.9854599833488464, "max": 2.8815367221832275, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9569.5546875, "min": 9569.5546875, "max": 29509.818359375, "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": 12.578500747680664, "min": 0.19108004868030548, "max": 12.578500747680664, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2452.8076171875, "min": 37.06953048706055, "max": 2524.880859375, "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.Losses.PolicyLoss.mean": { "value": 0.07006441180762041, "min": 0.06301057839386083, "max": 0.07316058867373595, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28025764723048163, "min": 0.2520423135754433, "max": 0.36580294336867974, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.12994428041080633, "min": 0.057764980759398614, "max": 0.18183373160221997, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5197771216432253, "min": 0.23105992303759446, "max": 0.9091686580110998, "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": 0.09999999999999998, "min": 0.09999999999999998, "max": 0.09999999999999998, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.3999999999999999, "min": 0.3999999999999999, "max": 0.4999999999999999, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.320060000000001e-05, "min": 2.320060000000001e-05, "max": 0.00048674060000000003, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 9.280240000000004e-05, "min": 9.280240000000004e-05, "max": 0.002312428, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.181818181818183, "min": 2.75, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 121.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 2.75, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 121.0, "max": 1380.0, "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": "1697022379", "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=SnowballTarget3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697022838" }, "total": 459.29682413800003, "count": 1, "self": 0.42865565100009917, "children": { "run_training.setup": { "total": 0.07023954599998206, "count": 1, "self": 0.07023954599998206 }, "TrainerController.start_learning": { "total": 458.79792894099995, "count": 1, "self": 0.5331379969945829, "children": { "TrainerController._reset_env": { "total": 8.022404402999996, "count": 1, "self": 8.022404402999996 }, "TrainerController.advance": { "total": 450.1529573780053, "count": 18201, "self": 0.27231736501255455, "children": { "env_step": { "total": 449.8806400129927, "count": 18201, "self": 308.3696353230033, "children": { "SubprocessEnvManager._take_step": { "total": 141.23643191399898, "count": 18201, "self": 1.3901599339927486, "children": { "TorchPolicy.evaluate": { "total": 139.84627198000624, "count": 18201, "self": 139.84627198000624 } } }, "workers": { "total": 0.2745727759904355, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 457.5795183950001, "count": 18201, "is_parallel": true, "self": 221.65946265499912, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006454921999988983, "count": 1, "is_parallel": true, "self": 0.0043369920000202455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021179299999687373, "count": 10, "is_parallel": true, "self": 0.0021179299999687373 } } }, "UnityEnvironment.step": { "total": 0.046302088999993884, "count": 1, "is_parallel": true, "self": 0.0007049269999868102, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041053000001056716, "count": 1, "is_parallel": true, "self": 0.00041053000001056716 }, "communicator.exchange": { "total": 0.0430446409999945, "count": 1, "is_parallel": true, "self": 0.0430446409999945 }, "steps_from_proto": { "total": 0.002141991000002008, "count": 1, "is_parallel": true, "self": 0.0005320419999748083, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016099490000271999, "count": 10, "is_parallel": true, "self": 0.0016099490000271999 } } } } } } }, "UnityEnvironment.step": { "total": 235.92005574000098, "count": 18200, "is_parallel": true, "self": 10.346040903989376, "children": { "UnityEnvironment._generate_step_input": { "total": 5.280943166008768, "count": 18200, "is_parallel": true, "self": 5.280943166008768 }, "communicator.exchange": { "total": 187.50584912600237, "count": 18200, "is_parallel": true, "self": 187.50584912600237 }, "steps_from_proto": { "total": 32.78722254400046, "count": 18200, "is_parallel": true, "self": 6.083201813000926, "children": { "_process_rank_one_or_two_observation": { "total": 26.70402073099953, "count": 182000, "is_parallel": true, "self": 26.70402073099953 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011632400003236398, "count": 1, "self": 0.00011632400003236398, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 446.50971218698254, "count": 461109, "is_parallel": true, "self": 9.826753579985109, "children": { "process_trajectory": { "total": 252.41192288799775, "count": 461109, "is_parallel": true, "self": 251.5467383439977, "children": { "RLTrainer._checkpoint": { "total": 0.8651845440000443, "count": 4, "is_parallel": true, "self": 0.8651845440000443 } } }, "_update_policy": { "total": 184.27103571899968, "count": 90, "is_parallel": true, "self": 57.27244771899555, "children": { "TorchPPOOptimizer.update": { "total": 126.99858800000413, "count": 4584, "is_parallel": true, "self": 126.99858800000413 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08931283900005837, "count": 1, "self": 0.0011601680000694614, "children": { "RLTrainer._checkpoint": { "total": 0.08815267099998891, "count": 1, "self": 0.08815267099998891 } } } } } } }