{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2920151948928833, "min": 1.2920151948928833, "max": 2.8781919479370117, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12336.1611328125, "min": 12336.1611328125, "max": 29475.564453125, "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": 11.57807445526123, "min": 0.0956335961818695, "max": 11.57807445526123, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2257.724609375, "min": 18.55291748046875, "max": 2321.87158203125, "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": 23.818181818181817, "min": 3.1136363636363638, "max": 23.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1048.0, "min": 137.0, "max": 1310.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.818181818181817, "min": 3.1136363636363638, "max": 23.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1048.0, "min": 137.0, "max": 1310.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0698207342695562, "min": 0.060932711576563575, "max": 0.07714702521565521, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.1396414685391124, "min": 0.12186542315312715, "max": 0.22348392762211788, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2497665174305439, "min": 0.10407096140786112, "max": 0.29827770824525873, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4995330348610878, "min": 0.20814192281572225, "max": 0.8948331247357761, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.432097856000005e-06, "min": 6.432097856000005e-06, "max": 0.000290232003256, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.286419571200001e-05, "min": 1.286419571200001e-05, "max": 0.0007419960526679999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10214399999999998, "min": 0.10214399999999998, "max": 0.19674400000000003, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20428799999999997, "min": 0.20428799999999997, "max": 0.5473319999999999, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011698560000000007, "min": 0.00011698560000000007, "max": 0.004837525599999998, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00023397120000000015, "min": 0.00023397120000000015, "max": 0.0123718668, "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": "1707060221", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707060685" }, "total": 463.507316253, "count": 1, "self": 0.43548252600010073, "children": { "run_training.setup": { "total": 0.04769677899992075, "count": 1, "self": 0.04769677899992075 }, "TrainerController.start_learning": { "total": 463.024136948, "count": 1, "self": 0.5529879370080835, "children": { "TrainerController._reset_env": { "total": 2.8380585329999803, "count": 1, "self": 2.8380585329999803 }, "TrainerController.advance": { "total": 459.53786780499183, "count": 18199, "self": 0.2731315289855729, "children": { "env_step": { "total": 459.26473627600626, "count": 18199, "self": 315.4500977999912, "children": { "SubprocessEnvManager._take_step": { "total": 143.5317963720064, "count": 18199, "self": 1.449297978011714, "children": { "TorchPolicy.evaluate": { "total": 142.08249839399468, "count": 18199, "self": 142.08249839399468 } } }, "workers": { "total": 0.28284210400863685, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 461.83864399198774, "count": 18199, "is_parallel": true, "self": 235.5936632799894, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00531576799994582, "count": 1, "is_parallel": true, "self": 0.003744649999930516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015711180000153036, "count": 10, "is_parallel": true, "self": 0.0015711180000153036 } } }, "UnityEnvironment.step": { "total": 0.07954577200007407, "count": 1, "is_parallel": true, "self": 0.0006651640001109627, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004156889999649138, "count": 1, "is_parallel": true, "self": 0.0004156889999649138 }, "communicator.exchange": { "total": 0.07633805399996163, "count": 1, "is_parallel": true, "self": 0.07633805399996163 }, "steps_from_proto": { "total": 0.0021268650000365596, "count": 1, "is_parallel": true, "self": 0.0003529609998622618, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017739040001742978, "count": 10, "is_parallel": true, "self": 0.0017739040001742978 } } } } } } }, "UnityEnvironment.step": { "total": 226.24498071199832, "count": 18198, "is_parallel": true, "self": 10.83575005599755, "children": { "UnityEnvironment._generate_step_input": { "total": 5.578157238995914, "count": 18198, "is_parallel": true, "self": 5.578157238995914 }, "communicator.exchange": { "total": 174.75809991700544, "count": 18198, "is_parallel": true, "self": 174.75809991700544 }, "steps_from_proto": { "total": 35.07297349999942, "count": 18198, "is_parallel": true, "self": 6.385974589016655, "children": { "_process_rank_one_or_two_observation": { "total": 28.686998910982766, "count": 181980, "is_parallel": true, "self": 28.686998910982766 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019675900011861813, "count": 1, "self": 0.00019675900011861813, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.05380389706147, "count": 850064, "is_parallel": true, "self": 18.449472416112144, "children": { "process_trajectory": { "total": 298.4617864539497, "count": 850064, "is_parallel": true, "self": 297.96559766394955, "children": { "RLTrainer._checkpoint": { "total": 0.49618879000013294, "count": 4, "is_parallel": true, "self": 0.49618879000013294 } } }, "_update_policy": { "total": 135.14254502699964, "count": 45, "is_parallel": true, "self": 46.698828245998584, "children": { "TorchPPOOptimizer.update": { "total": 88.44371678100106, "count": 4587, "is_parallel": true, "self": 88.44371678100106 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09502591399996163, "count": 1, "self": 0.0009602390000509331, "children": { "RLTrainer._checkpoint": { "total": 0.0940656749999107, "count": 1, "self": 0.0940656749999107 } } } } } } }