| { |
| "name": "root", |
| "gauges": { |
| "SnowballTarget.Policy.Entropy.mean": { |
| "value": 2.757416248321533, |
| "min": 2.753434896469116, |
| "max": 2.8903160095214844, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Entropy.sum": { |
| "value": 26388.47265625, |
| "min": 26388.47265625, |
| "max": 29663.3046875, |
| "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": 1.204874873161316, |
| "min": 0.0993828997015953, |
| "max": 1.218990683555603, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 234.9506072998047, |
| "min": 19.280282974243164, |
| "max": 248.0491943359375, |
| "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": 8.340909090909092, |
| "min": 2.5272727272727273, |
| "max": 8.75, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.sum": { |
| "value": 367.0, |
| "min": 120.0, |
| "max": 442.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.mean": { |
| "value": 8.340909090909092, |
| "min": 2.5272727272727273, |
| "max": 8.75, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.sum": { |
| "value": 367.0, |
| "min": 120.0, |
| "max": 442.0, |
| "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 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.mean": { |
| "value": 0.06926951290499775, |
| "min": 0.06926951290499775, |
| "max": 0.07453565245547604, |
| "count": 4 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.sum": { |
| "value": 0.06926951290499775, |
| "min": 0.06926951290499775, |
| "max": 0.07453565245547604, |
| "count": 4 |
| }, |
| "SnowballTarget.Losses.ValueLoss.mean": { |
| "value": 0.20801461134434737, |
| "min": 0.08423845381475985, |
| "max": 0.20801461134434737, |
| "count": 4 |
| }, |
| "SnowballTarget.Losses.ValueLoss.sum": { |
| "value": 0.20801461134434737, |
| "min": 0.08423845381475985, |
| "max": 0.20801461134434737, |
| "count": 4 |
| }, |
| "SnowballTarget.Policy.LearningRate.mean": { |
| "value": 5.3688082104e-05, |
| "min": 5.3688082104e-05, |
| "max": 0.0002384880205039999, |
| "count": 4 |
| }, |
| "SnowballTarget.Policy.LearningRate.sum": { |
| "value": 5.3688082104e-05, |
| "min": 5.3688082104e-05, |
| "max": 0.0002384880205039999, |
| "count": 4 |
| }, |
| "SnowballTarget.Policy.Epsilon.mean": { |
| "value": 0.117896, |
| "min": 0.117896, |
| "max": 0.17949600000000002, |
| "count": 4 |
| }, |
| "SnowballTarget.Policy.Epsilon.sum": { |
| "value": 0.117896, |
| "min": 0.117896, |
| "max": 0.17949600000000002, |
| "count": 4 |
| }, |
| "SnowballTarget.Policy.Beta.mean": { |
| "value": 0.0009030103999999999, |
| "min": 0.0009030103999999999, |
| "max": 0.003976850400000001, |
| "count": 4 |
| }, |
| "SnowballTarget.Policy.Beta.sum": { |
| "value": 0.0009030103999999999, |
| "min": 0.0009030103999999999, |
| "max": 0.003976850400000001, |
| "count": 4 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1714131468", |
| "python_version": "3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]", |
| "command_line_arguments": "/home/bloess/miniconda3/envs/hugging_face_rl_course/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": "2.2.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1714132188" |
| }, |
| "total": 719.862877041, |
| "count": 1, |
| "self": 0.6273972530000265, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0496171280000226, |
| "count": 1, |
| "self": 0.0496171280000226 |
| }, |
| "TrainerController.start_learning": { |
| "total": 719.18586266, |
| "count": 1, |
| "self": 0.6052117249818139, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 8.37451949199999, |
| "count": 1, |
| "self": 8.37451949199999 |
| }, |
| "TrainerController.advance": { |
| "total": 709.9857309960184, |
| "count": 18203, |
| "self": 0.24730891899775997, |
| "children": { |
| "env_step": { |
| "total": 709.7384220770207, |
| "count": 18203, |
| "self": 470.96975056503834, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 238.5034011429833, |
| "count": 18203, |
| "self": 1.7707324869802505, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 236.73266865600306, |
| "count": 18203, |
| "self": 236.73266865600306 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.26527036899904033, |
| "count": 18203, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 717.9234648069969, |
| "count": 18203, |
| "is_parallel": true, |
| "self": 403.40279559697944, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0015346449999924516, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004634009997062094, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0010712440002862422, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0010712440002862422 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.032535090000010314, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00027921100002004096, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00020505099996626086, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00020505099996626086 |
| }, |
| "communicator.exchange": { |
| "total": 0.03100810499995532, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.03100810499995532 |
| }, |
| "steps_from_proto": { |
| "total": 0.0010427230000686905, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00023787100019490026, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0008048519998737902, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0008048519998737902 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 314.52066921001745, |
| "count": 18202, |
| "is_parallel": true, |
| "self": 5.562252823020685, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 3.6369556919928527, |
| "count": 18202, |
| "is_parallel": true, |
| "self": 3.6369556919928527 |
| }, |
| "communicator.exchange": { |
| "total": 285.2324305680206, |
| "count": 18202, |
| "is_parallel": true, |
| "self": 285.2324305680206 |
| }, |
| "steps_from_proto": { |
| "total": 20.08903012698329, |
| "count": 18202, |
| "is_parallel": true, |
| "self": 4.418540646978386, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 15.670489480004903, |
| "count": 182020, |
| "is_parallel": true, |
| "self": 15.670489480004903 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.144999989985081e-05, |
| "count": 1, |
| "self": 9.144999989985081e-05, |
| "children": { |
| "thread_root": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "trainer_advance": { |
| "total": 701.7372546371329, |
| "count": 1025784, |
| "is_parallel": true, |
| "self": 23.311361457350813, |
| "children": { |
| "process_trajectory": { |
| "total": 540.4050824257821, |
| "count": 1025784, |
| "is_parallel": true, |
| "self": 539.3192922087818, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 1.0857902170002944, |
| "count": 4, |
| "is_parallel": true, |
| "self": 1.0857902170002944 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 138.02081075399997, |
| "count": 4, |
| "is_parallel": true, |
| "self": 31.981349483009353, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 106.03946127099061, |
| "count": 3846, |
| "is_parallel": true, |
| "self": 106.03946127099061 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "TrainerController._save_models": { |
| "total": 0.2203089969998473, |
| "count": 1, |
| "self": 0.01835148399982245, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.20195751300002485, |
| "count": 1, |
| "self": 0.20195751300002485 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
