{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0299615859985352, "min": 1.015785813331604, "max": 2.8709557056427, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9834.0732421875, "min": 9834.0732421875, "max": 29464.6171875, "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": 13.050840377807617, "min": 0.40749552845954895, "max": 13.050840377807617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2544.913818359375, "min": 79.05413055419922, "max": 2651.5205078125, "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": 0.07085555997978457, "min": 0.06047918515419132, "max": 0.07306364497886605, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2834222399191383, "min": 0.24191674061676527, "max": 0.3571563970455078, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17935572374685138, "min": 0.10171985432651698, "max": 0.2756335207936811, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7174228949874055, "min": 0.4068794173060679, "max": 1.3765901750793645, "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": 25.818181818181817, "min": 2.659090909090909, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 117.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 2.659090909090909, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 117.0, "max": 1399.0, "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": "1699534187", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699534658" }, "total": 470.7424795740001, "count": 1, "self": 0.4252515590001167, "children": { "run_training.setup": { "total": 0.07220463800001653, "count": 1, "self": 0.07220463800001653 }, "TrainerController.start_learning": { "total": 470.24502337699994, "count": 1, "self": 0.5583209029927048, "children": { "TrainerController._reset_env": { "total": 8.055348368999944, "count": 1, "self": 8.055348368999944 }, "TrainerController.advance": { "total": 461.5471156530074, "count": 18198, "self": 0.26687777001711765, "children": { "env_step": { "total": 461.28023788299026, "count": 18198, "self": 314.0023173129881, "children": { "SubprocessEnvManager._take_step": { "total": 146.99700421600824, "count": 18198, "self": 1.4394443510118435, "children": { "TorchPolicy.evaluate": { "total": 145.5575598649964, "count": 18198, "self": 145.5575598649964 } } }, "workers": { "total": 0.28091635399391635, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 469.0069092580071, "count": 18198, "is_parallel": true, "self": 229.03570583701378, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005284473999950023, "count": 1, "is_parallel": true, "self": 0.003709175999802028, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015752980001479955, "count": 10, "is_parallel": true, "self": 0.0015752980001479955 } } }, "UnityEnvironment.step": { "total": 0.06370107400005054, "count": 1, "is_parallel": true, "self": 0.0006891459998996652, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040799200007768377, "count": 1, "is_parallel": true, "self": 0.00040799200007768377 }, "communicator.exchange": { "total": 0.06031587899997248, "count": 1, "is_parallel": true, "self": 0.06031587899997248 }, "steps_from_proto": { "total": 0.0022880570001007072, "count": 1, "is_parallel": true, "self": 0.00043429800007288577, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018537590000278215, "count": 10, "is_parallel": true, "self": 0.0018537590000278215 } } } } } } }, "UnityEnvironment.step": { "total": 239.97120342099333, "count": 18197, "is_parallel": true, "self": 10.6688475419935, "children": { "UnityEnvironment._generate_step_input": { "total": 5.680183400007309, "count": 18197, "is_parallel": true, "self": 5.680183400007309 }, "communicator.exchange": { "total": 188.24173674799863, "count": 18197, "is_parallel": true, "self": 188.24173674799863 }, "steps_from_proto": { "total": 35.380435730993895, "count": 18197, "is_parallel": true, "self": 6.630385945012563, "children": { "_process_rank_one_or_two_observation": { "total": 28.750049785981332, "count": 181970, "is_parallel": true, "self": 28.750049785981332 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001515240001026541, "count": 1, "self": 0.0001515240001026541, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.57649235497865, "count": 487938, "is_parallel": true, "self": 10.483218377961975, "children": { "process_trajectory": { "total": 260.5987879800158, "count": 487938, "is_parallel": true, "self": 260.08499718201574, "children": { "RLTrainer._checkpoint": { "total": 0.5137907980000591, "count": 4, "is_parallel": true, "self": 0.5137907980000591 } } }, "_update_policy": { "total": 186.49448599700088, "count": 90, "is_parallel": true, "self": 56.24634105100313, "children": { "TorchPPOOptimizer.update": { "total": 130.24814494599775, "count": 4587, "is_parallel": true, "self": 130.24814494599775 } } } } } } } } }, "TrainerController._save_models": { "total": 0.084086927999806, "count": 1, "self": 0.0008795729997927992, "children": { "RLTrainer._checkpoint": { "total": 0.0832073550000132, "count": 1, "self": 0.0832073550000132 } } } } } } }