{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.023223876953125, "min": 1.023223876953125, "max": 2.8584296703338623, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9792.251953125, "min": 9792.251953125, "max": 29304.62109375, "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": 13.242210388183594, "min": 0.5126795172691345, "max": 13.242210388183594, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2582.23095703125, "min": 99.45983123779297, "max": 2697.012451171875, "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": 0.14187179216603052, "min": 0.13532572328244452, "max": 0.1461921186876626, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.5674871686641221, "min": 0.5413028931297781, "max": 0.708136206875566, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1682097071909583, "min": 0.14820671922887496, "max": 0.27055302904188344, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6728388287638332, "min": 0.5928268769154998, "max": 1.267983444181143, "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": 0.0013851600382799997, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102694, "min": 0.102694, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.410776, "min": 0.410776, "max": 0.9617200000000001, "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": 25.886363636363637, "min": 4.2272727272727275, "max": 26.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 186.0, "max": 1437.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 4.2272727272727275, "max": 26.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 186.0, "max": 1437.0, "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": "1684819487", "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": "1684820238" }, "total": 751.8498948429997, "count": 1, "self": 0.4919921909986442, "children": { "run_training.setup": { "total": 0.08990056600032403, "count": 1, "self": 0.08990056600032403 }, "TrainerController.start_learning": { "total": 751.2680020860007, "count": 1, "self": 0.8592243909797617, "children": { "TrainerController._reset_env": { "total": 1.3588328420000835, "count": 1, "self": 1.3588328420000835 }, "TrainerController.advance": { "total": 748.8992823650215, "count": 18205, "self": 0.42400054301288037, "children": { "env_step": { "total": 748.4752818220086, "count": 18205, "self": 644.381463711994, "children": { "SubprocessEnvManager._take_step": { "total": 103.68934317896401, "count": 18205, "self": 2.5872829858853947, "children": { "TorchPolicy.evaluate": { "total": 101.10206019307861, "count": 18205, "self": 101.10206019307861 } } }, "workers": { "total": 0.4044749310505722, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 748.7893580649352, "count": 18205, "is_parallel": true, "self": 409.11145441590725, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00884898499953124, "count": 1, "is_parallel": true, "self": 0.005533800000193878, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033151849993373617, "count": 10, "is_parallel": true, "self": 0.0033151849993373617 } } }, "UnityEnvironment.step": { "total": 0.12537986099960108, "count": 1, "is_parallel": true, "self": 0.0007538230001955526, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005093310001029749, "count": 1, "is_parallel": true, "self": 0.0005093310001029749 }, "communicator.exchange": { "total": 0.121623219999492, "count": 1, "is_parallel": true, "self": 0.121623219999492 }, "steps_from_proto": { "total": 0.002493486999810557, "count": 1, "is_parallel": true, "self": 0.000500709001244104, "children": { "_process_rank_one_or_two_observation": { "total": 0.001992777998566453, "count": 10, "is_parallel": true, "self": 0.001992777998566453 } } } } } } }, "UnityEnvironment.step": { "total": 339.67790364902794, "count": 18204, "is_parallel": true, "self": 14.882474572010324, "children": { "UnityEnvironment._generate_step_input": { "total": 7.84700864802835, "count": 18204, "is_parallel": true, "self": 7.84700864802835 }, "communicator.exchange": { "total": 269.1887783490247, "count": 18204, "is_parallel": true, "self": 269.1887783490247 }, "steps_from_proto": { "total": 47.75964207996458, "count": 18204, "is_parallel": true, "self": 9.368827044852878, "children": { "_process_rank_one_or_two_observation": { "total": 38.3908150351117, "count": 182040, "is_parallel": true, "self": 38.3908150351117 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001439399993614643, "count": 1, "self": 0.0001439399993614643, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 743.6054675754867, "count": 597908, "is_parallel": true, "self": 14.492270703322902, "children": { "process_trajectory": { "total": 318.6167387241667, "count": 597908, "is_parallel": true, "self": 316.33833086116556, "children": { "RLTrainer._checkpoint": { "total": 2.278407863001121, "count": 4, "is_parallel": true, "self": 2.278407863001121 } } }, "_update_policy": { "total": 410.49645814799715, "count": 90, "is_parallel": true, "self": 86.85191090803801, "children": { "TorchPPOOptimizer.update": { "total": 323.64454723995914, "count": 18354, "is_parallel": true, "self": 323.64454723995914 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1505185480000364, "count": 1, "self": 0.0011168300006829668, "children": { "RLTrainer._checkpoint": { "total": 0.14940171799935342, "count": 1, "self": 0.14940171799935342 } } } } } } }