{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8510521054267883, "min": 0.8510521054267883, "max": 2.8620758056640625, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8088.3994140625, "min": 8088.3994140625, "max": 29216.0703125, "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": 12.919587135314941, "min": 0.5393465757369995, "max": 12.919587135314941, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.319580078125, "min": 104.63323974609375, "max": 2638.06640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06563175951255379, "min": 0.0625585480693011, "max": 0.07887955555016364, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26252703805021516, "min": 0.2502341922772044, "max": 0.3943977777508182, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2122824835572757, "min": 0.15602081966376408, "max": 0.27261497319913375, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8491299342291028, "min": 0.6240832786550563, "max": 1.3630748659956688, "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.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.Environment.CumulativeReward.mean": { "value": 25.318181818181817, "min": 4.318181818181818, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 190.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 4.318181818181818, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 190.0, "max": 1418.0, "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": "1759134929", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1759135344" }, "total": 415.06099784799994, "count": 1, "self": 0.7986896910000496, "children": { "run_training.setup": { "total": 0.025314828999967176, "count": 1, "self": 0.025314828999967176 }, "TrainerController.start_learning": { "total": 414.2369933279999, "count": 1, "self": 0.3231690319903464, "children": { "TrainerController._reset_env": { "total": 2.996433901000046, "count": 1, "self": 2.996433901000046 }, "TrainerController.advance": { "total": 410.80081801700953, "count": 18192, "self": 0.341817999000682, "children": { "env_step": { "total": 295.70800646501516, "count": 18192, "self": 230.8852357439822, "children": { "SubprocessEnvManager._take_step": { "total": 64.62841682303281, "count": 18192, "self": 1.1488345340318347, "children": { "TorchPolicy.evaluate": { "total": 63.47958228900097, "count": 18192, "self": 63.47958228900097 } } }, "workers": { "total": 0.1943538980001449, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 412.2106310639924, "count": 18192, "is_parallel": true, "self": 209.10727043498753, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00471763899997768, "count": 1, "is_parallel": true, "self": 0.003284784999891599, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014328540000860812, "count": 10, "is_parallel": true, "self": 0.0014328540000860812 } } }, "UnityEnvironment.step": { "total": 0.03424647200006348, "count": 1, "is_parallel": true, "self": 0.0006125140000676765, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003887819999590647, "count": 1, "is_parallel": true, "self": 0.0003887819999590647 }, "communicator.exchange": { "total": 0.03135562099998879, "count": 1, "is_parallel": true, "self": 0.03135562099998879 }, "steps_from_proto": { "total": 0.0018895550000479489, "count": 1, "is_parallel": true, "self": 0.00042242100016665063, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014671339998812982, "count": 10, "is_parallel": true, "self": 0.0014671339998812982 } } } } } } }, "UnityEnvironment.step": { "total": 203.1033606290049, "count": 18191, "is_parallel": true, "self": 9.786123766989704, "children": { "UnityEnvironment._generate_step_input": { "total": 5.087350087989876, "count": 18191, "is_parallel": true, "self": 5.087350087989876 }, "communicator.exchange": { "total": 154.9316773949938, "count": 18191, "is_parallel": true, "self": 154.9316773949938 }, "steps_from_proto": { "total": 33.298209379031505, "count": 18191, "is_parallel": true, "self": 5.995652578050681, "children": { "_process_rank_one_or_two_observation": { "total": 27.302556800980824, "count": 181910, "is_parallel": true, "self": 27.302556800980824 } } } } } } } } } } }, "trainer_advance": { "total": 114.75099355299369, "count": 18192, "self": 0.3927194000102645, "children": { "process_trajectory": { "total": 25.00506939198067, "count": 18192, "self": 24.539091236980767, "children": { "RLTrainer._checkpoint": { "total": 0.46597815499990247, "count": 4, "self": 0.46597815499990247 } } }, "_update_policy": { "total": 89.35320476100276, "count": 90, "self": 36.32361317800269, "children": { "TorchPPOOptimizer.update": { "total": 53.02959158300007, "count": 4587, "self": 53.02959158300007 } } } } } } }, "trainer_threads": { "total": 1.1839999842777615e-06, "count": 1, "self": 1.1839999842777615e-06 }, "TrainerController._save_models": { "total": 0.11657119400001648, "count": 1, "self": 0.0009478879999278433, "children": { "RLTrainer._checkpoint": { "total": 0.11562330600008863, "count": 1, "self": 0.11562330600008863 } } } } } } }