{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8302021026611328, "min": 0.8302021026611328, "max": 2.8782455921173096, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8520.3642578125, "min": 8240.2080078125, "max": 29507.7734375, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.184460639953613, "min": 0.35725894570350647, "max": 13.18896198272705, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2689.6298828125, "min": 69.30823516845703, "max": 2696.407470703125, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07016346581846901, "min": 0.06261018357261883, "max": 0.07606870673172286, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35081732909234503, "min": 0.2504407342904753, "max": 0.3803435336586143, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19849070842359579, "min": 0.13108704224406909, "max": 0.2855049737674349, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.992453542117979, "min": 0.5243481689762763, "max": 1.3212304509737913, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.5254315706666646e-06, "min": 3.5254315706666646e-06, "max": 0.00019639200180400005, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.7627157853333323e-05, "min": 1.7627157853333323e-05, "max": 0.00094896002552, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.97448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804000000006, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999998, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.6, "min": 3.2954545454545454, "max": 26.054545454545455, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1408.0, "min": 145.0, "max": 1433.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.6, "min": 3.2954545454545454, "max": 26.054545454545455, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1408.0, "min": 145.0, "max": 1433.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709622540", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709623177" }, "total": 636.9537627970001, "count": 1, "self": 0.43438160400012293, "children": { "run_training.setup": { "total": 0.04906087699998807, "count": 1, "self": 0.04906087699998807 }, "TrainerController.start_learning": { "total": 636.470320316, "count": 1, "self": 0.8182911329979561, "children": { "TrainerController._reset_env": { "total": 3.3064533680000068, "count": 1, "self": 3.3064533680000068 }, "TrainerController.advance": { "total": 632.2536601190021, "count": 27332, "self": 0.3724649230008481, "children": { "env_step": { "total": 631.8811951960013, "count": 27332, "self": 405.44968545097475, "children": { "SubprocessEnvManager._take_step": { "total": 226.02945619701836, "count": 27332, "self": 2.0867117090122633, "children": { "TorchPolicy.evaluate": { "total": 223.9427444880061, "count": 27332, "self": 223.9427444880061 } } }, "workers": { "total": 0.40205354800815485, "count": 27332, "self": 0.0, "children": { "worker_root": { "total": 634.910365822011, "count": 27332, "is_parallel": true, "self": 317.3698741610138, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005236830000001191, "count": 1, "is_parallel": true, "self": 0.0036111739998432313, "children": { "_process_rank_one_or_two_observation": { "total": 0.00162565600015796, "count": 10, "is_parallel": true, "self": 0.00162565600015796 } } }, "UnityEnvironment.step": { "total": 0.03809372499995334, "count": 1, "is_parallel": true, "self": 0.0007135779999316583, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040767100000493883, "count": 1, "is_parallel": true, "self": 0.00040767100000493883 }, "communicator.exchange": { "total": 0.03487212499999259, "count": 1, "is_parallel": true, "self": 0.03487212499999259 }, "steps_from_proto": { "total": 0.0021003510000241477, "count": 1, "is_parallel": true, "self": 0.00046960100002024774, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016307500000039, "count": 10, "is_parallel": true, "self": 0.0016307500000039 } } } } } } }, "UnityEnvironment.step": { "total": 317.54049166099725, "count": 27331, "is_parallel": true, "self": 15.619649653011379, "children": { "UnityEnvironment._generate_step_input": { "total": 7.713544319001812, "count": 27331, "is_parallel": true, "self": 7.713544319001812 }, "communicator.exchange": { "total": 245.71628289900127, "count": 27331, "is_parallel": true, "self": 245.71628289900127 }, "steps_from_proto": { "total": 48.491014789982785, "count": 27331, "is_parallel": true, "self": 8.843670360015153, "children": { "_process_rank_one_or_two_observation": { "total": 39.64734442996763, "count": 273310, "is_parallel": true, "self": 39.64734442996763 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004568059998746321, "count": 1, "self": 0.0004568059998746321, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 624.5793353869763, "count": 962887, "is_parallel": true, "self": 20.048923227022442, "children": { "process_trajectory": { "total": 345.28379113595355, "count": 962887, "is_parallel": true, "self": 340.95320233995335, "children": { "RLTrainer._checkpoint": { "total": 4.3305887960002, "count": 30, "is_parallel": true, "self": 4.3305887960002 } } }, "_update_policy": { "total": 259.2466210240002, "count": 136, "is_parallel": true, "self": 76.02750755398978, "children": { "TorchPPOOptimizer.update": { "total": 183.21911347001043, "count": 6933, "is_parallel": true, "self": 183.21911347001043 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09145889000001262, "count": 1, "self": 0.0010628370000631548, "children": { "RLTrainer._checkpoint": { "total": 0.09039605299994946, "count": 1, "self": 0.09039605299994946 } } } } } } }