{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.738807201385498, "min": 2.738807201385498, "max": 2.856985092163086, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28228.88671875, "min": 28228.88671875, "max": 29258.384765625, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.431374430656433, "min": 0.4062758684158325, "max": 1.431374430656433, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 293.4317626953125, "min": 78.81752014160156, "max": 293.4317626953125, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06604825756056051, "min": 0.06604825756056051, "max": 0.06825368776851831, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3302412878028026, "min": 0.27301475107407325, "max": 0.3302412878028026, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18844070227122772, "min": 0.12298734749178859, "max": 0.18844070227122772, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9422035113561387, "min": 0.49194938996715437, "max": 0.9422035113561387, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.000277032007656, "min": 0.000277032007656, "max": 0.000291882002706, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00138516003828, "min": 0.001167528010824, "max": 0.00138516003828, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.19234400000000001, "min": 0.19234400000000001, "max": 0.19729400000000002, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.96172, "min": 0.7891760000000001, "max": 0.96172, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0046179656, "min": 0.0046179656, "max": 0.0048649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.023089828, "min": 0.0194598824, "max": 0.023089828, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 6.254545454545455, "min": 3.4545454545454546, "max": 6.254545454545455, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 344.0, "min": 152.0, "max": 344.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 6.254545454545455, "min": 3.4545454545454546, "max": 6.254545454545455, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 344.0, "min": 152.0, "max": 344.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704542944", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704543016" }, "total": 72.4438991500001, "count": 1, "self": 0.5669868800000586, "children": { "run_training.setup": { "total": 0.053265243000168994, "count": 1, "self": 0.053265243000168994 }, "TrainerController.start_learning": { "total": 71.82364702699988, "count": 1, "self": 0.10216607901566022, "children": { "TrainerController._reset_env": { "total": 1.9734478710001895, "count": 1, "self": 1.9734478710001895 }, "TrainerController.advance": { "total": 69.49619717598398, "count": 2536, "self": 0.04511832998105092, "children": { "env_step": { "total": 69.45107884600293, "count": 2536, "self": 44.939564022007744, "children": { "SubprocessEnvManager._take_step": { "total": 24.464884926987907, "count": 2536, "self": 0.23077119898516685, "children": { "TorchPolicy.evaluate": { "total": 24.23411372800274, "count": 2536, "self": 24.23411372800274 } } }, "workers": { "total": 0.04662989700727849, "count": 2535, "self": 0.0, "children": { "worker_root": { "total": 71.38363162900168, "count": 2535, "is_parallel": true, "self": 35.90804179299903, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002493408000191266, "count": 1, "is_parallel": true, "self": 0.0007671119997212372, "children": { "_process_rank_one_or_two_observation": { "total": 0.001726296000470029, "count": 10, "is_parallel": true, "self": 0.001726296000470029 } } }, "UnityEnvironment.step": { "total": 0.044670830000086426, "count": 1, "is_parallel": true, "self": 0.0008115389996419253, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042173700012426707, "count": 1, "is_parallel": true, "self": 0.00042173700012426707 }, "communicator.exchange": { "total": 0.04063515100006043, "count": 1, "is_parallel": true, "self": 0.04063515100006043 }, "steps_from_proto": { "total": 0.002802403000259801, "count": 1, "is_parallel": true, "self": 0.0004477700003917562, "children": { "_process_rank_one_or_two_observation": { "total": 0.002354632999868045, "count": 10, "is_parallel": true, "self": 0.002354632999868045 } } } } } } }, "UnityEnvironment.step": { "total": 35.475589836002655, "count": 2534, "is_parallel": true, "self": 1.6721596260190381, "children": { "UnityEnvironment._generate_step_input": { "total": 0.862624660001984, "count": 2534, "is_parallel": true, "self": 0.862624660001984 }, "communicator.exchange": { "total": 27.6160652590047, "count": 2534, "is_parallel": true, "self": 27.6160652590047 }, "steps_from_proto": { "total": 5.3247402909769335, "count": 2534, "is_parallel": true, "self": 0.9923920869923677, "children": { "_process_rank_one_or_two_observation": { "total": 4.332348203984566, "count": 25340, "is_parallel": true, "self": 4.332348203984566 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.858100030309288e-05, "count": 1, "self": 5.858100030309288e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 68.57400567399691, "count": 106941, "is_parallel": true, "self": 2.286718173990721, "children": { "process_trajectory": { "total": 39.04175350100695, "count": 106941, "is_parallel": true, "self": 39.04175350100695 }, "_update_policy": { "total": 27.245533998999235, "count": 12, "is_parallel": true, "self": 8.039025478992698, "children": { "TorchPPOOptimizer.update": { "total": 19.206508520006537, "count": 609, "is_parallel": true, "self": 19.206508520006537 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2517773199997464, "count": 1, "self": 0.001305043999764166, "children": { "RLTrainer._checkpoint": { "total": 0.25047227599998223, "count": 1, "self": 0.25047227599998223 } } } } } } }