{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9193209409713745, "min": 0.9193209409713745, "max": 2.8601338863372803, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8808.013671875, "min": 8808.013671875, "max": 29322.09375, "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": 12.930448532104492, "min": 0.22459860146045685, "max": 12.930448532104492, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2521.4375, "min": 43.57212829589844, "max": 2634.97998046875, "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": 0.06553240325507326, "min": 0.0625059275756654, "max": 0.0755836467352114, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26212961302029303, "min": 0.2570274986014114, "max": 0.36655959638957547, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2123196436932274, "min": 0.10607056042485341, "max": 0.3009559067294878, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8492785747729096, "min": 0.42428224169941364, "max": 1.4137468755829568, "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.CumulativeReward.mean": { "value": 25.34090909090909, "min": 3.0681818181818183, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 135.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 3.0681818181818183, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 135.0, "max": 1406.0, "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": "1685236643", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "1685237090" }, "total": 446.565222761, "count": 1, "self": 0.4924770999999737, "children": { "run_training.setup": { "total": 0.04067739499998879, "count": 1, "self": 0.04067739499998879 }, "TrainerController.start_learning": { "total": 446.032068266, "count": 1, "self": 0.501746198001797, "children": { "TrainerController._reset_env": { "total": 5.0707979490000525, "count": 1, "self": 5.0707979490000525 }, "TrainerController.advance": { "total": 440.2443522819981, "count": 18209, "self": 0.2430332640110464, "children": { "env_step": { "total": 440.00131901798704, "count": 18209, "self": 319.69615874396186, "children": { "SubprocessEnvManager._take_step": { "total": 120.05974389300707, "count": 18209, "self": 1.6906239799897094, "children": { "TorchPolicy.evaluate": { "total": 118.36911991301736, "count": 18209, "self": 118.36911991301736 } } }, "workers": { "total": 0.24541638101811714, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 444.4375564279884, "count": 18209, "is_parallel": true, "self": 210.28989729300383, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00642241399998511, "count": 1, "is_parallel": true, "self": 0.004432661000464577, "children": { "_process_rank_one_or_two_observation": { "total": 0.001989752999520533, "count": 10, "is_parallel": true, "self": 0.001989752999520533 } } }, "UnityEnvironment.step": { "total": 0.033211131999905774, "count": 1, "is_parallel": true, "self": 0.0005359399998496883, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002468390000558429, "count": 1, "is_parallel": true, "self": 0.0002468390000558429 }, "communicator.exchange": { "total": 0.030493062999994436, "count": 1, "is_parallel": true, "self": 0.030493062999994436 }, "steps_from_proto": { "total": 0.001935290000005807, "count": 1, "is_parallel": true, "self": 0.00036360099977628124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015716890002295258, "count": 10, "is_parallel": true, "self": 0.0015716890002295258 } } } } } } }, "UnityEnvironment.step": { "total": 234.14765913498456, "count": 18208, "is_parallel": true, "self": 9.329205166987549, "children": { "UnityEnvironment._generate_step_input": { "total": 5.02749712099569, "count": 18208, "is_parallel": true, "self": 5.02749712099569 }, "communicator.exchange": { "total": 188.20071838499177, "count": 18208, "is_parallel": true, "self": 188.20071838499177 }, "steps_from_proto": { "total": 31.59023846200955, "count": 18208, "is_parallel": true, "self": 5.945309370931454, "children": { "_process_rank_one_or_two_observation": { "total": 25.644929091078097, "count": 182080, "is_parallel": true, "self": 25.644929091078097 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012192400004096271, "count": 1, "self": 0.00012192400004096271, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 436.647018992942, "count": 434431, "is_parallel": true, "self": 9.40867747597133, "children": { "process_trajectory": { "total": 238.5617264489706, "count": 434431, "is_parallel": true, "self": 237.21917949297062, "children": { "RLTrainer._checkpoint": { "total": 1.3425469559999783, "count": 4, "is_parallel": true, "self": 1.3425469559999783 } } }, "_update_policy": { "total": 188.67661506800005, "count": 90, "is_parallel": true, "self": 71.67159794699535, "children": { "TorchPPOOptimizer.update": { "total": 117.0050171210047, "count": 4587, "is_parallel": true, "self": 117.0050171210047 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21504991300002985, "count": 1, "self": 0.001092966999976852, "children": { "RLTrainer._checkpoint": { "total": 0.213956946000053, "count": 1, "self": 0.213956946000053 } } } } } } }