{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9020084738731384, "min": 0.9001221656799316, "max": 2.8555939197540283, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8602.455078125, "min": 8602.455078125, "max": 29275.548828125, "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": 12.955206871032715, "min": 0.35989347100257874, "max": 13.054583549499512, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.265380859375, "min": 69.8193359375, "max": 2663.135009765625, "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": 0.07285431207406766, "min": 0.06506779216027223, "max": 0.07295032190364402, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29141724829627064, "min": 0.2602711686410889, "max": 0.34825919565457086, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21647592345435246, "min": 0.1145247080450074, "max": 0.300472750324829, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8659036938174098, "min": 0.4580988321800296, "max": 1.502363751624145, "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": 24.295454545454547, "min": 3.2045454545454546, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1069.0, "min": 141.0, "max": 1421.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.295454545454547, "min": 3.2045454545454546, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1069.0, "min": 141.0, "max": 1421.0, "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": "1725556223", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725556724" }, "total": 500.2395847790001, "count": 1, "self": 0.4394897439999568, "children": { "run_training.setup": { "total": 0.08034708700006377, "count": 1, "self": 0.08034708700006377 }, "TrainerController.start_learning": { "total": 499.7197479480001, "count": 1, "self": 0.6057831340067423, "children": { "TrainerController._reset_env": { "total": 2.2502718230000482, "count": 1, "self": 2.2502718230000482 }, "TrainerController.advance": { "total": 496.76044613499334, "count": 18200, "self": 0.28304512099566637, "children": { "env_step": { "total": 496.4774010139977, "count": 18200, "self": 306.4995596940007, "children": { "SubprocessEnvManager._take_step": { "total": 189.67996846598476, "count": 18200, "self": 1.5709082410055544, "children": { "TorchPolicy.evaluate": { "total": 188.1090602249792, "count": 18200, "self": 188.1090602249792 } } }, "workers": { "total": 0.297872854012212, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 498.42653804898987, "count": 18200, "is_parallel": true, "self": 261.87591429800295, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002792474999978367, "count": 1, "is_parallel": true, "self": 0.0007077389996084094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020847360003699578, "count": 10, "is_parallel": true, "self": 0.0020847360003699578 } } }, "UnityEnvironment.step": { "total": 0.0870935840000584, "count": 1, "is_parallel": true, "self": 0.0007116809999843099, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000413369999932911, "count": 1, "is_parallel": true, "self": 0.000413369999932911 }, "communicator.exchange": { "total": 0.08399911300011809, "count": 1, "is_parallel": true, "self": 0.08399911300011809 }, "steps_from_proto": { "total": 0.001969420000023092, "count": 1, "is_parallel": true, "self": 0.00042739899981825147, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015420210002048407, "count": 10, "is_parallel": true, "self": 0.0015420210002048407 } } } } } } }, "UnityEnvironment.step": { "total": 236.55062375098692, "count": 18199, "is_parallel": true, "self": 10.672343726987037, "children": { "UnityEnvironment._generate_step_input": { "total": 5.657376187998807, "count": 18199, "is_parallel": true, "self": 5.657376187998807 }, "communicator.exchange": { "total": 183.49579485998402, "count": 18199, "is_parallel": true, "self": 183.49579485998402 }, "steps_from_proto": { "total": 36.725108976017054, "count": 18199, "is_parallel": true, "self": 6.942399407045514, "children": { "_process_rank_one_or_two_observation": { "total": 29.78270956897154, "count": 181990, "is_parallel": true, "self": 29.78270956897154 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001851590000114811, "count": 1, "self": 0.0001851590000114811, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 490.218491764934, "count": 748205, "is_parallel": true, "self": 16.16019111085552, "children": { "process_trajectory": { "total": 272.40504990307977, "count": 748205, "is_parallel": true, "self": 271.27014323807975, "children": { "RLTrainer._checkpoint": { "total": 1.1349066650000168, "count": 4, "is_parallel": true, "self": 1.1349066650000168 } } }, "_update_policy": { "total": 201.65325075099872, "count": 90, "is_parallel": true, "self": 65.56214720100161, "children": { "TorchPPOOptimizer.update": { "total": 136.09110354999711, "count": 4584, "is_parallel": true, "self": 136.09110354999711 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10306169699993006, "count": 1, "self": 0.0013181859997075662, "children": { "RLTrainer._checkpoint": { "total": 0.1017435110002225, "count": 1, "self": 0.1017435110002225 } } } } } } }