{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9939660429954529, "min": 0.9939660429954529, "max": 2.8652021884918213, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9479.4541015625, "min": 9479.4541015625, "max": 29311.01953125, "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": 12.92700481414795, "min": 0.4379461705684662, "max": 12.92700481414795, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.765869140625, "min": 84.96155548095703, "max": 2602.91162109375, "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": 0.06831065804084681, "min": 0.0626622470016717, "max": 0.07513917923286358, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27324263216338723, "min": 0.26026461880103974, "max": 0.37569589616431787, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2101042000759466, "min": 0.12116368229765737, "max": 0.30508264482897873, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8404168003037864, "min": 0.48465472919062946, "max": 1.3995190990321775, "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": 25.636363636363637, "min": 3.6136363636363638, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 159.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.6136363636363638, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 159.0, "max": 1391.0, "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": "1729234572", "python_version": "3.10.0 (default, Mar 3 2022, 09:58:08) [GCC 7.5.0]", "command_line_arguments": "/cpfs/user/taishan/miniconda3/envs/ml-agents/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729235248" }, "total": 675.8216114540119, "count": 1, "self": 0.4927448020025622, "children": { "run_training.setup": { "total": 0.1348289480083622, "count": 1, "self": 0.1348289480083622 }, "TrainerController.start_learning": { "total": 675.194037704001, "count": 1, "self": 0.3895529267756501, "children": { "TrainerController._reset_env": { "total": 2.5233453170076245, "count": 1, "self": 2.5233453170076245 }, "TrainerController.advance": { "total": 672.1429772242263, "count": 18199, "self": 0.1763634559320053, "children": { "env_step": { "total": 671.9666137682943, "count": 18199, "self": 616.15568793274, "children": { "SubprocessEnvManager._take_step": { "total": 55.62823329062667, "count": 18199, "self": 1.0695501794252777, "children": { "TorchPolicy.evaluate": { "total": 54.55868311120139, "count": 18199, "self": 54.55868311120139 } } }, "workers": { "total": 0.18269254492770415, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 674.647071604224, "count": 18199, "is_parallel": true, "self": 89.59817719628336, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017549710028106347, "count": 1, "is_parallel": true, "self": 0.00048598401190247387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012689869909081608, "count": 10, "is_parallel": true, "self": 0.0012689869909081608 } } }, "UnityEnvironment.step": { "total": 0.10893234799732454, "count": 1, "is_parallel": true, "self": 0.00012919699656777084, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005732089921366423, "count": 1, "is_parallel": true, "self": 0.0005732089921366423 }, "communicator.exchange": { "total": 0.10716004700225312, "count": 1, "is_parallel": true, "self": 0.10716004700225312 }, "steps_from_proto": { "total": 0.0010698950063670054, "count": 1, "is_parallel": true, "self": 0.00019747103215195239, "children": { "_process_rank_one_or_two_observation": { "total": 0.000872423974215053, "count": 10, "is_parallel": true, "self": 0.000872423974215053 } } } } } } }, "UnityEnvironment.step": { "total": 585.0488944079407, "count": 18198, "is_parallel": true, "self": 2.013568172536907, "children": { "UnityEnvironment._generate_step_input": { "total": 8.28632280988677, "count": 18198, "is_parallel": true, "self": 8.28632280988677 }, "communicator.exchange": { "total": 556.3046126269328, "count": 18198, "is_parallel": true, "self": 556.3046126269328 }, "steps_from_proto": { "total": 18.44439079858421, "count": 18198, "is_parallel": true, "self": 3.042698417790234, "children": { "_process_rank_one_or_two_observation": { "total": 15.401692380793975, "count": 181980, "is_parallel": true, "self": 15.401692380793975 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016436800069641322, "count": 1, "self": 0.00016436800069641322, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 668.1478758146113, "count": 1140311, "is_parallel": true, "self": 11.041638071212219, "children": { "process_trajectory": { "total": 429.85108414143906, "count": 1140311, "is_parallel": true, "self": 429.19270904143923, "children": { "RLTrainer._checkpoint": { "total": 0.6583750999998301, "count": 4, "is_parallel": true, "self": 0.6583750999998301 } } }, "_update_policy": { "total": 227.25515360196005, "count": 90, "is_parallel": true, "self": 26.137329098768532, "children": { "TorchPPOOptimizer.update": { "total": 201.1178245031915, "count": 4587, "is_parallel": true, "self": 201.1178245031915 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1379978679906344, "count": 1, "self": 0.022744437999790534, "children": { "RLTrainer._checkpoint": { "total": 0.11525342999084387, "count": 1, "self": 0.11525342999084387 } } } } } } }