{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9611567258834839, "min": 0.960245668888092, "max": 2.873363494873047, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9219.4150390625, "min": 9219.4150390625, "max": 29489.330078125, "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": 12.695014953613281, "min": 0.48521721363067627, "max": 12.695014953613281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2475.52783203125, "min": 94.13214111328125, "max": 2571.57080078125, "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": 0.07018589115471638, "min": 0.059921010171213616, "max": 0.07280895195806664, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2807435646188655, "min": 0.23968404068485447, "max": 0.3527972586761119, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19607250728443557, "min": 0.13469567725905127, "max": 0.28123013751179565, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7842900291377423, "min": 0.5387827090362051, "max": 1.4061506875589782, "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": 25.0, "min": 3.7045454545454546, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 163.0, "max": 1363.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.7045454545454546, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 163.0, "max": 1363.0, "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": "1673693649", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/home/chqma/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1673694153" }, "total": 504.3206708279904, "count": 1, "self": 0.682776139001362, "children": { "run_training.setup": { "total": 0.038449906976893544, "count": 1, "self": 0.038449906976893544 }, "TrainerController.start_learning": { "total": 503.59944478201214, "count": 1, "self": 0.5777903320849873, "children": { "TrainerController._reset_env": { "total": 8.413715916045476, "count": 1, "self": 8.413715916045476 }, "TrainerController.advance": { "total": 494.206432274892, "count": 18209, "self": 0.24656838533701375, "children": { "env_step": { "total": 493.959863889555, "count": 18209, "self": 320.8063900108682, "children": { "SubprocessEnvManager._take_step": { "total": 172.91391268151347, "count": 18209, "self": 1.628965024894569, "children": { "TorchPolicy.evaluate": { "total": 171.2849476566189, "count": 18209, "self": 171.2849476566189 } } }, "workers": { "total": 0.23956119717331603, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 502.26671385311056, "count": 18209, "is_parallel": true, "self": 259.2373300208128, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014928299933671951, "count": 1, "is_parallel": true, "self": 0.00048610701924189925, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010067229741252959, "count": 10, "is_parallel": true, "self": 0.0010067229741252959 } } }, "UnityEnvironment.step": { "total": 0.023810248996596783, "count": 1, "is_parallel": true, "self": 0.00025625695707276464, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026645901380106807, "count": 1, "is_parallel": true, "self": 0.00026645901380106807 }, "communicator.exchange": { "total": 0.02256404800573364, "count": 1, "is_parallel": true, "self": 0.02256404800573364 }, "steps_from_proto": { "total": 0.0007234850199893117, "count": 1, "is_parallel": true, "self": 0.0001519140205346048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005715709994547069, "count": 10, "is_parallel": true, "self": 0.0005715709994547069 } } } } } } }, "UnityEnvironment.step": { "total": 243.02938383229775, "count": 18208, "is_parallel": true, "self": 5.322614489297848, "children": { "UnityEnvironment._generate_step_input": { "total": 3.0695946764899418, "count": 18208, "is_parallel": true, "self": 3.0695946764899418 }, "communicator.exchange": { "total": 219.7852737486246, "count": 18208, "is_parallel": true, "self": 219.7852737486246 }, "steps_from_proto": { "total": 14.85190091788536, "count": 18208, "is_parallel": true, "self": 3.2453711943817325, "children": { "_process_rank_one_or_two_observation": { "total": 11.606529723503627, "count": 182080, "is_parallel": true, "self": 11.606529723503627 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011403596727177501, "count": 1, "self": 0.00011403596727177501, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 490.9085112269968, "count": 390411, "is_parallel": true, "self": 9.526077080867253, "children": { "process_trajectory": { "total": 275.625926771143, "count": 390411, "is_parallel": true, "self": 274.39828912110534, "children": { "RLTrainer._checkpoint": { "total": 1.22763765003765, "count": 4, "is_parallel": true, "self": 1.22763765003765 } } }, "_update_policy": { "total": 205.75650737498654, "count": 90, "is_parallel": true, "self": 33.882790918054525, "children": { "TorchPPOOptimizer.update": { "total": 171.87371645693202, "count": 4587, "is_parallel": true, "self": 171.87371645693202 } } } } } } } } }, "TrainerController._save_models": { "total": 0.4013922230224125, "count": 1, "self": 0.059237569046672434, "children": { "RLTrainer._checkpoint": { "total": 0.3421546539757401, "count": 1, "self": 0.3421546539757401 } } } } } } }