{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9611240029335022, "min": 0.9611240029335022, "max": 2.870668411254883, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9208.529296875, "min": 9208.529296875, "max": 29493.24609375, "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": 12.886453628540039, "min": 0.12745146453380585, "max": 12.886453628540039, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2512.8583984375, "min": 24.725584030151367, "max": 2608.973388671875, "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": 0.02948186376306694, "min": 0.0246977459845463, "max": 0.0439102855574068, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.11792745505226776, "min": 0.11020644035549292, "max": 0.19158418172931607, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2630194667726755, "min": 0.08696804653542736, "max": 0.35716924133400124, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.052077867090702, "min": 0.34787218614170945, "max": 1.6631768743197122, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.3470097306000012e-05, "min": 1.3470097306000012e-05, "max": 0.0004864700027059999, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.388038922400005e-05, "min": 5.388038922400005e-05, "max": 0.0023086000382799995, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102694, "min": 0.102694, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.410776, "min": 0.410776, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.15909090909091, "min": 2.3181818181818183, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 102.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 2.3181818181818183, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 102.0, "max": 1399.0, "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": "1696074669", "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": "1696075146" }, "total": 476.364926833, "count": 1, "self": 0.728611944000022, "children": { "run_training.setup": { "total": 0.06784996700002921, "count": 1, "self": 0.06784996700002921 }, "TrainerController.start_learning": { "total": 475.568464922, "count": 1, "self": 0.6272391240144088, "children": { "TrainerController._reset_env": { "total": 4.563847365000015, "count": 1, "self": 4.563847365000015 }, "TrainerController.advance": { "total": 470.15366331598557, "count": 18220, "self": 0.3112912829800507, "children": { "env_step": { "total": 469.8423720330055, "count": 18220, "self": 329.7984289530083, "children": { "SubprocessEnvManager._take_step": { "total": 139.72135108798682, "count": 18220, "self": 1.9331178199985288, "children": { "TorchPolicy.evaluate": { "total": 137.7882332679883, "count": 18220, "self": 137.7882332679883 } } }, "workers": { "total": 0.3225919920104161, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 473.85951140599343, "count": 18220, "is_parallel": true, "self": 209.44645221199414, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006545200000005025, "count": 1, "is_parallel": true, "self": 0.004258105000189971, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022870949998150536, "count": 10, "is_parallel": true, "self": 0.0022870949998150536 } } }, "UnityEnvironment.step": { "total": 0.038489846000061334, "count": 1, "is_parallel": true, "self": 0.0006342040001072746, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004213710000158244, "count": 1, "is_parallel": true, "self": 0.0004213710000158244 }, "communicator.exchange": { "total": 0.034170812999946065, "count": 1, "is_parallel": true, "self": 0.034170812999946065 }, "steps_from_proto": { "total": 0.00326345799999217, "count": 1, "is_parallel": true, "self": 0.000395182999568533, "children": { "_process_rank_one_or_two_observation": { "total": 0.002868275000423637, "count": 10, "is_parallel": true, "self": 0.002868275000423637 } } } } } } }, "UnityEnvironment.step": { "total": 264.4130591939993, "count": 18219, "is_parallel": true, "self": 11.103997732988887, "children": { "UnityEnvironment._generate_step_input": { "total": 5.615584456005763, "count": 18219, "is_parallel": true, "self": 5.615584456005763 }, "communicator.exchange": { "total": 208.78344992100176, "count": 18219, "is_parallel": true, "self": 208.78344992100176 }, "steps_from_proto": { "total": 38.91002708400288, "count": 18219, "is_parallel": true, "self": 7.356285168006934, "children": { "_process_rank_one_or_two_observation": { "total": 31.553741915995943, "count": 182190, "is_parallel": true, "self": 31.553741915995943 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014679199989586778, "count": 1, "self": 0.00014679199989586778, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.7452535329471, "count": 519945, "is_parallel": true, "self": 11.909701606007275, "children": { "process_trajectory": { "total": 304.9401219779395, "count": 519945, "is_parallel": true, "self": 303.5740258359393, "children": { "RLTrainer._checkpoint": { "total": 1.366096142000174, "count": 4, "is_parallel": true, "self": 1.366096142000174 } } }, "_update_policy": { "total": 148.89542994900035, "count": 90, "is_parallel": true, "self": 92.65198936100126, "children": { "TorchPPOOptimizer.update": { "total": 56.24344058799909, "count": 1080, "is_parallel": true, "self": 56.24344058799909 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2235683250000875, "count": 1, "self": 0.0011112570002751454, "children": { "RLTrainer._checkpoint": { "total": 0.22245706799981235, "count": 1, "self": 0.22245706799981235 } } } } } } }