{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.934207558631897, "min": 0.934207558631897, "max": 2.867465019226074, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8950.642578125, "min": 8950.642578125, "max": 29460.3359375, "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": 13.09872817993164, "min": 0.4238336980342865, "max": 13.09872817993164, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2554.251953125, "min": 82.22373962402344, "max": 2646.197021484375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07062556181906485, "min": 0.06280792511556772, "max": 0.07748617742931946, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2825022472762594, "min": 0.25636284870515563, "max": 0.36000188174012676, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20878279939586042, "min": 0.13515346862065294, "max": 0.28102919453499364, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8351311975834417, "min": 0.5406138744826118, "max": 1.4051459726749682, "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": 25.568181818181817, "min": 3.9545454545454546, "max": 26.2, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 174.0, "max": 1441.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 3.9545454545454546, "max": 26.2, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 174.0, "max": 1441.0, "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": "1699949893", "python_version": "3.10.3 (main, Mar 28 2022, 09:30:03) [GCC 7.5.0]", "command_line_arguments": "/home/yzeng/anaconda3/envs/deeprl_course_unit5/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./ml-agents/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": "2.1.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1699950153" }, "total": 259.91941927326843, "count": 1, "self": 0.26910326117649674, "children": { "run_training.setup": { "total": 0.010970384813845158, "count": 1, "self": 0.010970384813845158 }, "TrainerController.start_learning": { "total": 259.6393456272781, "count": 1, "self": 0.3781122420914471, "children": { "TrainerController._reset_env": { "total": 0.7038590121082962, "count": 1, "self": 0.7038590121082962 }, "TrainerController.advance": { "total": 258.50105012208223, "count": 18206, "self": 0.19063659012317657, "children": { "env_step": { "total": 258.31041353195906, "count": 18206, "self": 198.23354557948187, "children": { "SubprocessEnvManager._take_step": { "total": 59.89203985687345, "count": 18206, "self": 0.9140398884192109, "children": { "TorchPolicy.evaluate": { "total": 58.97799996845424, "count": 18206, "self": 58.97799996845424 } } }, "workers": { "total": 0.18482809560373425, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 259.16482363594696, "count": 18206, "is_parallel": true, "self": 125.7474294253625, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013139499351382256, "count": 1, "is_parallel": true, "self": 0.0003613196313381195, "children": { "_process_rank_one_or_two_observation": { "total": 0.000952630303800106, "count": 10, "is_parallel": true, "self": 0.000952630303800106 } } }, "UnityEnvironment.step": { "total": 0.0184068251401186, "count": 1, "is_parallel": true, "self": 0.0002597835846245289, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019907066598534584, "count": 1, "is_parallel": true, "self": 0.00019907066598534584 }, "communicator.exchange": { "total": 0.017071345821022987, "count": 1, "is_parallel": true, "self": 0.017071345821022987 }, "steps_from_proto": { "total": 0.0008766250684857368, "count": 1, "is_parallel": true, "self": 0.0002001458778977394, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006764791905879974, "count": 10, "is_parallel": true, "self": 0.0006764791905879974 } } } } } } }, "UnityEnvironment.step": { "total": 133.41739421058446, "count": 18205, "is_parallel": true, "self": 5.946274475660175, "children": { "UnityEnvironment._generate_step_input": { "total": 3.3883161335252225, "count": 18205, "is_parallel": true, "self": 3.3883161335252225 }, "communicator.exchange": { "total": 105.14979411428794, "count": 18205, "is_parallel": true, "self": 105.14979411428794 }, "steps_from_proto": { "total": 18.93300948711112, "count": 18205, "is_parallel": true, "self": 3.8589850193820894, "children": { "_process_rank_one_or_two_observation": { "total": 15.074024467729032, "count": 182050, "is_parallel": true, "self": 15.074024467729032 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.70400869846344e-05, "count": 1, "self": 9.70400869846344e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 258.2991554606706, "count": 116475, "is_parallel": true, "self": 1.4075341755524278, "children": { "process_trajectory": { "total": 142.83908892422915, "count": 116475, "is_parallel": true, "self": 142.44756823405623, "children": { "RLTrainer._checkpoint": { "total": 0.3915206901729107, "count": 4, "is_parallel": true, "self": 0.3915206901729107 } } }, "_update_policy": { "total": 114.05253236088902, "count": 90, "is_parallel": true, "self": 27.892967737279832, "children": { "TorchPPOOptimizer.update": { "total": 86.15956462360919, "count": 4587, "is_parallel": true, "self": 86.15956462360919 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05622721090912819, "count": 1, "self": 0.0006280425004661083, "children": { "RLTrainer._checkpoint": { "total": 0.05559916840866208, "count": 1, "self": 0.05559916840866208 } } } } } } }