{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9140366315841675, "min": 0.9119477272033691, "max": 2.869006633758545, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8687.00390625, "min": 8687.00390625, "max": 29286.8203125, "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": 13.012314796447754, "min": 0.38760048151016235, "max": 13.012314796447754, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.4013671875, "min": 75.19449615478516, "max": 2632.580078125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07005985597902954, "min": 0.06286683942319132, "max": 0.07658928449918498, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28023942391611817, "min": 0.25487151318481543, "max": 0.3829464224959249, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19468781242475788, "min": 0.11722935040883134, "max": 0.2776451954070259, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7787512496990315, "min": 0.46891740163532536, "max": 1.3882259770351297, "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.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.Environment.CumulativeReward.mean": { "value": 25.681818181818183, "min": 3.2045454545454546, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1130.0, "min": 141.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.681818181818183, "min": 3.2045454545454546, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1130.0, "min": 141.0, "max": 1398.0, "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": "1744189804", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/POWERCOM.CO/essam/miniconda3/envs/hf_rl_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744189940" }, "total": 136.77127434394788, "count": 1, "self": 0.21691214805468917, "children": { "run_training.setup": { "total": 0.009813846903853118, "count": 1, "self": 0.009813846903853118 }, "TrainerController.start_learning": { "total": 136.54454834898934, "count": 1, "self": 0.14031236432492733, "children": { "TrainerController._reset_env": { "total": 1.2417038140119985, "count": 1, "self": 1.2417038140119985 }, "TrainerController.advance": { "total": 135.11468956572935, "count": 18192, "self": 0.14425743010360748, "children": { "env_step": { "total": 94.11857598938514, "count": 18192, "self": 71.81006459984928, "children": { "SubprocessEnvManager._take_step": { "total": 22.215316139743663, "count": 18192, "self": 0.5376267161918804, "children": { "TorchPolicy.evaluate": { "total": 21.677689423551783, "count": 18192, "self": 21.677689423551783 } } }, "workers": { "total": 0.0931952497921884, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 136.22584927128628, "count": 18192, "is_parallel": true, "self": 73.57121688185725, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000757095986045897, "count": 1, "is_parallel": true, "self": 0.00021054001990705729, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005465559661388397, "count": 10, "is_parallel": true, "self": 0.0005465559661388397 } } }, "UnityEnvironment.step": { "total": 0.01176439190749079, "count": 1, "is_parallel": true, "self": 0.00016164092812687159, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00011937995441257954, "count": 1, "is_parallel": true, "self": 0.00011937995441257954 }, "communicator.exchange": { "total": 0.011023355997167528, "count": 1, "is_parallel": true, "self": 0.011023355997167528 }, "steps_from_proto": { "total": 0.0004600150277838111, "count": 1, "is_parallel": true, "self": 0.00010373699478805065, "children": { "_process_rank_one_or_two_observation": { "total": 0.00035627803299576044, "count": 10, "is_parallel": true, "self": 0.00035627803299576044 } } } } } } }, "UnityEnvironment.step": { "total": 62.654632389429025, "count": 18191, "is_parallel": true, "self": 2.6548123008105904, "children": { "UnityEnvironment._generate_step_input": { "total": 1.2705923336325213, "count": 18191, "is_parallel": true, "self": 1.2705923336325213 }, "communicator.exchange": { "total": 51.377839326742105, "count": 18191, "is_parallel": true, "self": 51.377839326742105 }, "steps_from_proto": { "total": 7.3513884282438084, "count": 18191, "is_parallel": true, "self": 1.4643805746454746, "children": { "_process_rank_one_or_two_observation": { "total": 5.887007853598334, "count": 181910, "is_parallel": true, "self": 5.887007853598334 } } } } } } } } } } }, "trainer_advance": { "total": 40.85185614624061, "count": 18192, "self": 0.1648165419464931, "children": { "process_trajectory": { "total": 9.523805722594261, "count": 18192, "self": 9.316269047558308, "children": { "RLTrainer._checkpoint": { "total": 0.20753667503595352, "count": 4, "self": 0.20753667503595352 } } }, "_update_policy": { "total": 31.163233881699853, "count": 90, "self": 13.142040552571416, "children": { "TorchPPOOptimizer.update": { "total": 18.021193329128437, "count": 4587, "self": 18.021193329128437 } } } } } } }, "trainer_threads": { "total": 5.499459803104401e-07, "count": 1, "self": 5.499459803104401e-07 }, "TrainerController._save_models": { "total": 0.047842054977081716, "count": 1, "self": 0.0015494339168071747, "children": { "RLTrainer._checkpoint": { "total": 0.04629262106027454, "count": 1, "self": 0.04629262106027454 } } } } } } }