{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8441686630249023, "min": 0.8441686630249023, "max": 2.871239185333252, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8050.83642578125, "min": 8050.83642578125, "max": 29372.77734375, "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": 12.993959426879883, "min": 0.2630867660045624, "max": 12.993959426879883, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.822021484375, "min": 51.03883361816406, "max": 2618.63037109375, "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": 0.06948945624069038, "min": 0.06201119307515197, "max": 0.07423860222579427, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2779578249627615, "min": 0.24804477230060787, "max": 0.37119301112897135, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19756650701895648, "min": 0.10566313002559849, "max": 0.30153941304660314, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7902660280758259, "min": 0.42265252010239396, "max": 1.3938179977384269, "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": 25.84090909090909, "min": 3.090909090909091, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1137.0, "min": 136.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.84090909090909, "min": 3.090909090909091, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1137.0, "min": 136.0, "max": 1415.0, "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": "1700154102", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700154604" }, "total": 502.35995868400005, "count": 1, "self": 0.7906019990000459, "children": { "run_training.setup": { "total": 0.07296706500005712, "count": 1, "self": 0.07296706500005712 }, "TrainerController.start_learning": { "total": 501.49638961999995, "count": 1, "self": 0.6495832899950074, "children": { "TrainerController._reset_env": { "total": 8.798982468999952, "count": 1, "self": 8.798982468999952 }, "TrainerController.advance": { "total": 491.92038092100495, "count": 18204, "self": 0.3146741170126006, "children": { "env_step": { "total": 491.60570680399235, "count": 18204, "self": 339.0497773479975, "children": { "SubprocessEnvManager._take_step": { "total": 152.2353009289959, "count": 18204, "self": 1.5863792399995873, "children": { "TorchPolicy.evaluate": { "total": 150.64892168899632, "count": 18204, "self": 150.64892168899632 } } }, "workers": { "total": 0.32062852699891664, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 499.83919157899163, "count": 18204, "is_parallel": true, "self": 240.95780052200826, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0076921050000464675, "count": 1, "is_parallel": true, "self": 0.005449647999739682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022424570003067856, "count": 10, "is_parallel": true, "self": 0.0022424570003067856 } } }, "UnityEnvironment.step": { "total": 0.06552012300005572, "count": 1, "is_parallel": true, "self": 0.0006380760000865848, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003875419999985752, "count": 1, "is_parallel": true, "self": 0.0003875419999985752 }, "communicator.exchange": { "total": 0.062444893000019874, "count": 1, "is_parallel": true, "self": 0.062444893000019874 }, "steps_from_proto": { "total": 0.0020496119999506845, "count": 1, "is_parallel": true, "self": 0.0003644929998927182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016851190000579663, "count": 10, "is_parallel": true, "self": 0.0016851190000579663 } } } } } } }, "UnityEnvironment.step": { "total": 258.8813910569834, "count": 18203, "is_parallel": true, "self": 11.06817828800206, "children": { "UnityEnvironment._generate_step_input": { "total": 5.592213340002218, "count": 18203, "is_parallel": true, "self": 5.592213340002218 }, "communicator.exchange": { "total": 206.92956483999126, "count": 18203, "is_parallel": true, "self": 206.92956483999126 }, "steps_from_proto": { "total": 35.29143458898784, "count": 18203, "is_parallel": true, "self": 6.980554716060169, "children": { "_process_rank_one_or_two_observation": { "total": 28.31087987292767, "count": 182030, "is_parallel": true, "self": 28.31087987292767 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016235899988714664, "count": 1, "self": 0.00016235899988714664, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 487.93016638804204, "count": 514605, "is_parallel": true, "self": 10.725942998065989, "children": { "process_trajectory": { "total": 275.5798138519766, "count": 514605, "is_parallel": true, "self": 274.24029960097687, "children": { "RLTrainer._checkpoint": { "total": 1.3395142509997413, "count": 4, "is_parallel": true, "self": 1.3395142509997413 } } }, "_update_policy": { "total": 201.62440953799944, "count": 90, "is_parallel": true, "self": 64.44281431099535, "children": { "TorchPPOOptimizer.update": { "total": 137.1815952270041, "count": 4584, "is_parallel": true, "self": 137.1815952270041 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12728058100015005, "count": 1, "self": 0.001159382000196274, "children": { "RLTrainer._checkpoint": { "total": 0.12612119899995378, "count": 1, "self": 0.12612119899995378 } } } } } } }