{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3216626644134521, "min": 1.3216626644134521, "max": 2.8621602058410645, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12633.7734375, "min": 12633.7734375, "max": 29342.8671875, "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": 11.15221881866455, "min": 0.4606693685054779, "max": 11.15221881866455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2174.6826171875, "min": 89.36985778808594, "max": 2246.8583984375, "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": 0.06745796325798009, "min": 0.06547828897429794, "max": 0.0750620869230439, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26983185303192037, "min": 0.2619131558971918, "max": 0.37092264364108296, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23677171251791365, "min": 0.13618129985201555, "max": 0.287140055833494, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9470868500716546, "min": 0.5447251994080622, "max": 1.3700488948938894, "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": 22.386363636363637, "min": 3.9545454545454546, "max": 22.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 985.0, "min": 174.0, "max": 1201.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.386363636363637, "min": 3.9545454545454546, "max": 22.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 985.0, "min": 174.0, "max": 1201.0, "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": "1720132264", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720132751" }, "total": 486.9316786669997, "count": 1, "self": 0.32178640099846234, "children": { "run_training.setup": { "total": 0.06706072600081825, "count": 1, "self": 0.06706072600081825 }, "TrainerController.start_learning": { "total": 486.5428315400004, "count": 1, "self": 0.5451643998912914, "children": { "TrainerController._reset_env": { "total": 2.0434746549999545, "count": 1, "self": 2.0434746549999545 }, "TrainerController.advance": { "total": 483.8644312021088, "count": 18202, "self": 0.26966234111569065, "children": { "env_step": { "total": 483.5947688609931, "count": 18202, "self": 351.38398292710554, "children": { "SubprocessEnvManager._take_step": { "total": 131.9260643959151, "count": 18202, "self": 1.4657761158923677, "children": { "TorchPolicy.evaluate": { "total": 130.46028828002272, "count": 18202, "self": 130.46028828002272 } } }, "workers": { "total": 0.284721537972473, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 485.7481144841022, "count": 18202, "is_parallel": true, "self": 218.7277927760888, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035449650004011346, "count": 1, "is_parallel": true, "self": 0.0009287710017815698, "children": { "_process_rank_one_or_two_observation": { "total": 0.002616193998619565, "count": 10, "is_parallel": true, "self": 0.002616193998619565 } } }, "UnityEnvironment.step": { "total": 0.03137366600003588, "count": 1, "is_parallel": true, "self": 0.0005332970004019444, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036676099989563227, "count": 1, "is_parallel": true, "self": 0.00036676099989563227 }, "communicator.exchange": { "total": 0.02899952799998573, "count": 1, "is_parallel": true, "self": 0.02899952799998573 }, "steps_from_proto": { "total": 0.0014740799997525755, "count": 1, "is_parallel": true, "self": 0.00030003600204508984, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011740439977074857, "count": 10, "is_parallel": true, "self": 0.0011740439977074857 } } } } } } }, "UnityEnvironment.step": { "total": 267.0203217080134, "count": 18201, "is_parallel": true, "self": 12.9772659659493, "children": { "UnityEnvironment._generate_step_input": { "total": 6.5675187540146, "count": 18201, "is_parallel": true, "self": 6.5675187540146 }, "communicator.exchange": { "total": 212.15816193800765, "count": 18201, "is_parallel": true, "self": 212.15816193800765 }, "steps_from_proto": { "total": 35.317375050041846, "count": 18201, "is_parallel": true, "self": 7.140087697934177, "children": { "_process_rank_one_or_two_observation": { "total": 28.17728735210767, "count": 182010, "is_parallel": true, "self": 28.17728735210767 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021655799992004177, "count": 1, "self": 0.00021655799992004177, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 479.5679776684983, "count": 454967, "is_parallel": true, "self": 11.0545563777996, "children": { "process_trajectory": { "total": 270.50230632769126, "count": 454967, "is_parallel": true, "self": 269.759009308691, "children": { "RLTrainer._checkpoint": { "total": 0.7432970190002379, "count": 4, "is_parallel": true, "self": 0.7432970190002379 } } }, "_update_policy": { "total": 198.01111496300746, "count": 90, "is_parallel": true, "self": 37.46776406698973, "children": { "TorchPPOOptimizer.update": { "total": 160.54335089601773, "count": 4587, "is_parallel": true, "self": 160.54335089601773 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08954472500045085, "count": 1, "self": 0.0011649640000541694, "children": { "RLTrainer._checkpoint": { "total": 0.08837976100039668, "count": 1, "self": 0.08837976100039668 } } } } } } }