{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9060644507408142, "min": 0.9060644507408142, "max": 2.867532968521118, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8641.13671875, "min": 8641.13671875, "max": 29366.404296875, "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": 12.711706161499023, "min": 0.31340494751930237, "max": 12.711706161499023, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2478.78271484375, "min": 60.800559997558594, "max": 2592.624755859375, "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": 0.07480476550927943, "min": 0.06099791923306304, "max": 0.07480476550927943, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29921906203711773, "min": 0.2449189175317502, "max": 0.35412562573693834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22850308998250496, "min": 0.11497446925918042, "max": 0.27417246288820807, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9140123599300198, "min": 0.4598978770367217, "max": 1.3643457907087664, "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": 25.045454545454547, "min": 3.340909090909091, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 147.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.340909090909091, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 147.0, "max": 1380.0, "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": "1704143437", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704143938" }, "total": 501.3883198620001, "count": 1, "self": 0.4356878930000221, "children": { "run_training.setup": { "total": 0.05025664400000096, "count": 1, "self": 0.05025664400000096 }, "TrainerController.start_learning": { "total": 500.9023753250001, "count": 1, "self": 0.6942556970002443, "children": { "TrainerController._reset_env": { "total": 3.0123304989999724, "count": 1, "self": 3.0123304989999724 }, "TrainerController.advance": { "total": 497.10121873599974, "count": 18199, "self": 0.34813011300229846, "children": { "env_step": { "total": 496.75308862299744, "count": 18199, "self": 330.5121833960193, "children": { "SubprocessEnvManager._take_step": { "total": 165.87941207599465, "count": 18199, "self": 1.724170855002967, "children": { "TorchPolicy.evaluate": { "total": 164.15524122099168, "count": 18199, "self": 164.15524122099168 } } }, "workers": { "total": 0.361493150983506, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 499.3078793690174, "count": 18199, "is_parallel": true, "self": 242.63521159203947, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004656339000121079, "count": 1, "is_parallel": true, "self": 0.0033385709996309743, "children": { "_process_rank_one_or_two_observation": { "total": 0.001317768000490105, "count": 10, "is_parallel": true, "self": 0.001317768000490105 } } }, "UnityEnvironment.step": { "total": 0.03880678999985321, "count": 1, "is_parallel": true, "self": 0.0006532539998715947, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041743799988580577, "count": 1, "is_parallel": true, "self": 0.00041743799988580577 }, "communicator.exchange": { "total": 0.035702086999890525, "count": 1, "is_parallel": true, "self": 0.035702086999890525 }, "steps_from_proto": { "total": 0.0020340110002052825, "count": 1, "is_parallel": true, "self": 0.0003785779997542704, "children": { "_process_rank_one_or_two_observation": { "total": 0.001655433000451012, "count": 10, "is_parallel": true, "self": 0.001655433000451012 } } } } } } }, "UnityEnvironment.step": { "total": 256.67266777697796, "count": 18198, "is_parallel": true, "self": 11.856169526003669, "children": { "UnityEnvironment._generate_step_input": { "total": 6.119519560995968, "count": 18198, "is_parallel": true, "self": 6.119519560995968 }, "communicator.exchange": { "total": 200.71370799997794, "count": 18198, "is_parallel": true, "self": 200.71370799997794 }, "steps_from_proto": { "total": 37.98327069000038, "count": 18198, "is_parallel": true, "self": 7.344003064969911, "children": { "_process_rank_one_or_two_observation": { "total": 30.63926762503047, "count": 181980, "is_parallel": true, "self": 30.63926762503047 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013613400005851872, "count": 1, "self": 0.00013613400005851872, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 490.78542296588694, "count": 761395, "is_parallel": true, "self": 16.04017440076359, "children": { "process_trajectory": { "total": 273.84041883212467, "count": 761395, "is_parallel": true, "self": 273.1473338451244, "children": { "RLTrainer._checkpoint": { "total": 0.6930849870002476, "count": 4, "is_parallel": true, "self": 0.6930849870002476 } } }, "_update_policy": { "total": 200.90482973299868, "count": 90, "is_parallel": true, "self": 61.28352509199317, "children": { "TorchPPOOptimizer.update": { "total": 139.6213046410055, "count": 4587, "is_parallel": true, "self": 139.6213046410055 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09443425900008151, "count": 1, "self": 0.0010390410000127304, "children": { "RLTrainer._checkpoint": { "total": 0.09339521800006878, "count": 1, "self": 0.09339521800006878 } } } } } } }