{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9413411617279053, "min": 0.9413411617279053, "max": 2.870241403579712, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9008.634765625, "min": 9008.634765625, "max": 29362.5703125, "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": 11.732173919677734, "min": 0.32061684131622314, "max": 11.732173919677734, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2287.77392578125, "min": 62.19966506958008, "max": 2379.99267578125, "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": 0.060807245479629596, "min": 0.060807245479629596, "max": 0.0752370564763017, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24322898191851838, "min": 0.24322898191851838, "max": 0.36262575804493297, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18288812096066334, "min": 0.12176244848581286, "max": 0.2760176760308882, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7315524838426534, "min": 0.48704979394325143, "max": 1.3800883801544412, "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": 23.068181818181817, "min": 3.1363636363636362, "max": 23.163636363636364, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1015.0, "min": 138.0, "max": 1274.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.068181818181817, "min": 3.1363636363636362, "max": 23.163636363636364, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1015.0, "min": 138.0, "max": 1274.0, "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": "1702583400", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702583880" }, "total": 480.442192651, "count": 1, "self": 0.7158475179999755, "children": { "run_training.setup": { "total": 0.05872199300000602, "count": 1, "self": 0.05872199300000602 }, "TrainerController.start_learning": { "total": 479.66762314000005, "count": 1, "self": 0.6626821419890234, "children": { "TrainerController._reset_env": { "total": 3.009640078000018, "count": 1, "self": 3.009640078000018 }, "TrainerController.advance": { "total": 475.862073541011, "count": 18210, "self": 0.3208464709967416, "children": { "env_step": { "total": 475.54122707001426, "count": 18210, "self": 315.46668393701935, "children": { "SubprocessEnvManager._take_step": { "total": 159.74911102700014, "count": 18210, "self": 1.5952501189887016, "children": { "TorchPolicy.evaluate": { "total": 158.15386090801144, "count": 18210, "self": 158.15386090801144 } } }, "workers": { "total": 0.32543210599476424, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 478.12681180899494, "count": 18210, "is_parallel": true, "self": 233.41050914400108, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004423970000004829, "count": 1, "is_parallel": true, "self": 0.00312166500003741, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013023049999674186, "count": 10, "is_parallel": true, "self": 0.0013023049999674186 } } }, "UnityEnvironment.step": { "total": 0.07274561299999505, "count": 1, "is_parallel": true, "self": 0.0007257489999688005, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004469450000215147, "count": 1, "is_parallel": true, "self": 0.0004469450000215147 }, "communicator.exchange": { "total": 0.0696227550000117, "count": 1, "is_parallel": true, "self": 0.0696227550000117 }, "steps_from_proto": { "total": 0.0019501639999930376, "count": 1, "is_parallel": true, "self": 0.00042948099996920064, "children": { "_process_rank_one_or_two_observation": { "total": 0.001520683000023837, "count": 10, "is_parallel": true, "self": 0.001520683000023837 } } } } } } }, "UnityEnvironment.step": { "total": 244.71630266499386, "count": 18209, "is_parallel": true, "self": 11.367536724001354, "children": { "UnityEnvironment._generate_step_input": { "total": 5.841175257997463, "count": 18209, "is_parallel": true, "self": 5.841175257997463 }, "communicator.exchange": { "total": 191.2664950619956, "count": 18209, "is_parallel": true, "self": 191.2664950619956 }, "steps_from_proto": { "total": 36.24109562099943, "count": 18209, "is_parallel": true, "self": 6.961631860985051, "children": { "_process_rank_one_or_two_observation": { "total": 29.27946376001438, "count": 182090, "is_parallel": true, "self": 29.27946376001438 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011896199998773227, "count": 1, "self": 0.00011896199998773227, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.87613273002336, "count": 717733, "is_parallel": true, "self": 15.268791899994369, "children": { "process_trajectory": { "total": 261.30199099802894, "count": 717733, "is_parallel": true, "self": 260.23943367902905, "children": { "RLTrainer._checkpoint": { "total": 1.0625573189998931, "count": 4, "is_parallel": true, "self": 1.0625573189998931 } } }, "_update_policy": { "total": 193.30534983200005, "count": 90, "is_parallel": true, "self": 60.51435561199992, "children": { "TorchPPOOptimizer.update": { "total": 132.79099422000013, "count": 4587, "is_parallel": true, "self": 132.79099422000013 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13310841700001674, "count": 1, "self": 0.0012928740001143524, "children": { "RLTrainer._checkpoint": { "total": 0.1318155429999024, "count": 1, "self": 0.1318155429999024 } } } } } } }