{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.836672842502594, "min": 0.836672842502594, "max": 1.8354339599609375, "count": 14 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8043.77294921875, "min": 8043.77294921875, "max": 17563.78515625, "count": 14 }, "SnowballTarget.Step.mean": { "value": 199960.0, "min": 69968.0, "max": 199960.0, "count": 14 }, "SnowballTarget.Step.sum": { "value": 199960.0, "min": 69968.0, "max": 199960.0, "count": 14 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.781302452087402, "min": 7.125820159912109, "max": 12.781302452087402, "count": 14 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2492.35400390625, "min": 833.720947265625, "max": 2593.813720703125, "count": 14 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 14 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 4378.0, "max": 10945.0, "count": 14 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06581170070064984, "min": 0.065043459268054, "max": 0.08029949526946224, "count": 14 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2632468028025994, "min": 0.1312331338658445, "max": 0.4014974763473112, "count": 14 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1939256189792764, "min": 0.18633982268910781, "max": 0.25311718063027255, "count": 14 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7757024759171056, "min": 0.5029456494558675, "max": 1.2505602845374275, "count": 14 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.214097262000005e-06, "min": 8.214097262000005e-06, "max": 0.00019961403346200002, "count": 14 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.285638904800002e-05, "min": 3.285638904800002e-05, "max": 0.00094032018656, "count": 14 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10273800000000001, "min": 0.10273800000000001, "max": 0.16653800000000002, "count": 14 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41095200000000004, "min": 0.33307600000000004, "max": 0.8134400000000002, "count": 14 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001466262000000001, "min": 0.0001466262000000001, "max": 0.0033302462000000007, "count": 14 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005865048000000004, "min": 0.0005865048000000004, "max": 0.015690656000000004, "count": 14 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.09090909090909, "min": 17.727272727272727, "max": 25.431818181818183, "count": 14 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1104.0, "min": 390.0, "max": 1388.0, "count": 14 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.09090909090909, "min": 17.727272727272727, "max": 25.431818181818183, "count": 14 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1104.0, "min": 390.0, "max": 1388.0, "count": 14 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692545544", "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 --resume", "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": "1692545861" }, "total": 317.6313503980001, "count": 1, "self": 0.7840919160000794, "children": { "run_training.setup": { "total": 0.04170700500003477, "count": 1, "self": 0.04170700500003477 }, "TrainerController.start_learning": { "total": 316.805551477, "count": 1, "self": 0.38119174001519696, "children": { "TrainerController._reset_env": { "total": 3.9177380400000175, "count": 1, "self": 3.9177380400000175 }, "TrainerController.advance": { "total": 312.27118551198475, "count": 12424, "self": 0.18747485698986566, "children": { "env_step": { "total": 312.0837106549949, "count": 12424, "self": 228.62752408799213, "children": { "SubprocessEnvManager._take_step": { "total": 83.26534969100692, "count": 12424, "self": 1.2040676890179611, "children": { "TorchPolicy.evaluate": { "total": 82.06128200198896, "count": 12424, "self": 82.06128200198896 } } }, "workers": { "total": 0.1908368759958421, "count": 12424, "self": 0.0, "children": { "worker_root": { "total": 315.55860512299535, "count": 12424, "is_parallel": true, "self": 147.2086571580037, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018325449999565535, "count": 1, "is_parallel": true, "self": 0.0005223669999168123, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013101780000397412, "count": 10, "is_parallel": true, "self": 0.0013101780000397412 } } }, "UnityEnvironment.step": { "total": 0.03423124400001143, "count": 1, "is_parallel": true, "self": 0.0005997139998044076, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004083150000724345, "count": 1, "is_parallel": true, "self": 0.0004083150000724345 }, "communicator.exchange": { "total": 0.031070490000047357, "count": 1, "is_parallel": true, "self": 0.031070490000047357 }, "steps_from_proto": { "total": 0.00215272500008723, "count": 1, "is_parallel": true, "self": 0.0005045410002821882, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016481839998050418, "count": 10, "is_parallel": true, "self": 0.0016481839998050418 } } } } } } }, "UnityEnvironment.step": { "total": 168.34994796499166, "count": 12423, "is_parallel": true, "self": 7.057714106998219, "children": { "UnityEnvironment._generate_step_input": { "total": 3.5819989389972307, "count": 12423, "is_parallel": true, "self": 3.5819989389972307 }, "communicator.exchange": { "total": 133.4748783099982, "count": 12423, "is_parallel": true, "self": 133.4748783099982 }, "steps_from_proto": { "total": 24.235356608998018, "count": 12423, "is_parallel": true, "self": 4.414643972016165, "children": { "_process_rank_one_or_two_observation": { "total": 19.820712636981852, "count": 124230, "is_parallel": true, "self": 19.820712636981852 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011547899998731737, "count": 1, "self": 0.00011547899998731737, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 309.8994989799986, "count": 283728, "is_parallel": true, "self": 6.091263030016762, "children": { "process_trajectory": { "total": 169.19533811698216, "count": 283728, "is_parallel": true, "self": 167.65719715898217, "children": { "RLTrainer._checkpoint": { "total": 1.5381409579999854, "count": 3, "is_parallel": true, "self": 1.5381409579999854 } } }, "_update_policy": { "total": 134.6128978329997, "count": 61, "is_parallel": true, "self": 53.76158820299975, "children": { "TorchPPOOptimizer.update": { "total": 80.85130962999995, "count": 3108, "is_parallel": true, "self": 80.85130962999995 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23532070600003863, "count": 1, "self": 0.0019433209999988321, "children": { "RLTrainer._checkpoint": { "total": 0.2333773850000398, "count": 1, "self": 0.2333773850000398 } } } } } } }