{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9051458835601807, "min": 0.8958672881126404, "max": 2.8793461322784424, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9120.25, "min": 8070.8681640625, "max": 32116.2265625, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499912.0, "min": 9952.0, "max": 499912.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499912.0, "min": 9952.0, "max": 499912.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.552339553833008, "min": 0.1313910037279129, "max": 14.569454193115234, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1469.7862548828125, "min": 12.744927406311035, "max": 1497.137451171875, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 13134.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.11320754716981, "min": 2.522727272727273, "max": 28.772727272727273, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1490.0, "min": 111.0, "max": 1579.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.11320754716981, "min": 2.522727272727273, "max": 28.772727272727273, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1490.0, "min": 111.0, "max": 1579.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04314950444711619, "min": 0.04314950444711619, "max": 0.05254254118121667, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.08629900889423238, "min": 0.08629900889423238, "max": 0.15762762354365, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15211700192269156, "min": 0.0761607040596359, "max": 0.2938694961807307, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.3042340038453831, "min": 0.1523214081192718, "max": 0.8294430902775596, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0000990000000026e-06, "min": 3.0000990000000026e-06, "max": 0.00029604000132, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 6.000198000000005e-06, "min": 6.000198000000005e-06, "max": 0.0008366400211199997, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101, "min": 0.101, "max": 0.19867999999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.202, "min": 0.202, "max": 0.5788800000000001, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 5.9900000000000047e-05, "min": 5.9900000000000047e-05, "max": 0.004934132000000001, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00011980000000000009, "min": 0.00011980000000000009, "max": 0.013946112, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681200148", "python_version": "3.8.13 (default, Oct 21 2022, 23:50:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/chenoi1/miniconda3/envs/dxtorch/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1", "numpy_version": "1.21.2", "end_time_seconds": "1681200713" }, "total": 565.5419128559988, "count": 1, "self": 0.16774363999502384, "children": { "run_training.setup": { "total": 0.02683232400158886, "count": 1, "self": 0.02683232400158886 }, "TrainerController.start_learning": { "total": 565.3473368920022, "count": 1, "self": 0.760026288953668, "children": { "TrainerController._reset_env": { "total": 0.4120313419989543, "count": 1, "self": 0.4120313419989543 }, "TrainerController.advance": { "total": 564.1072649360503, "count": 45543, "self": 0.3256897511309944, "children": { "env_step": { "total": 563.7815751849193, "count": 45543, "self": 432.97451339550025, "children": { "SubprocessEnvManager._take_step": { "total": 130.45971468850985, "count": 45543, "self": 1.3622235474322224, "children": { "TorchPolicy.evaluate": { "total": 129.09749114107763, "count": 45543, "self": 129.09749114107763 } } }, "workers": { "total": 0.34734710090924636, "count": 45543, "self": 0.0, "children": { "worker_root": { "total": 563.9830406965339, "count": 45543, "is_parallel": true, "self": 237.55084753948177, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013660969998454675, "count": 1, "is_parallel": true, "self": 0.000625291999313049, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007408050005324185, "count": 10, "is_parallel": true, "self": 0.0007408050005324185 } } }, "UnityEnvironment.step": { "total": 0.017025307002768386, "count": 1, "is_parallel": true, "self": 0.00018508100401959382, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001588810009707231, "count": 1, "is_parallel": true, "self": 0.0001588810009707231 }, "communicator.exchange": { "total": 0.016050547998020193, "count": 1, "is_parallel": true, "self": 0.016050547998020193 }, "steps_from_proto": { "total": 0.0006307969997578766, "count": 1, "is_parallel": true, "self": 0.0001695300052233506, "children": { "_process_rank_one_or_two_observation": { "total": 0.000461266994534526, "count": 10, "is_parallel": true, "self": 0.000461266994534526 } } } } } } }, "UnityEnvironment.step": { "total": 326.4321931570521, "count": 45542, "is_parallel": true, "self": 6.737098305497057, "children": { "UnityEnvironment._generate_step_input": { "total": 4.0071289960505965, "count": 45542, "is_parallel": true, "self": 4.0071289960505965 }, "communicator.exchange": { "total": 295.8229425705176, "count": 45542, "is_parallel": true, "self": 295.8229425705176 }, "steps_from_proto": { "total": 19.86502328498682, "count": 45542, "is_parallel": true, "self": 4.0616002690767345, "children": { "_process_rank_one_or_two_observation": { "total": 15.803423015910084, "count": 455420, "is_parallel": true, "self": 15.803423015910084 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0007740990004094783, "count": 1, "self": 0.0007740990004094783, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 563.530333786719, "count": 249787, "is_parallel": true, "self": 3.260401939831354, "children": { "process_trajectory": { "total": 241.44248771587445, "count": 249787, "is_parallel": true, "self": 240.37768866787883, "children": { "RLTrainer._checkpoint": { "total": 1.0647990479956206, "count": 10, "is_parallel": true, "self": 1.0647990479956206 } } }, "_update_policy": { "total": 318.8274441310132, "count": 113, "is_parallel": true, "self": 75.21916118503577, "children": { "TorchPPOOptimizer.update": { "total": 243.6082829459774, "count": 9605, "is_parallel": true, "self": 243.6082829459774 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06724022599883028, "count": 1, "self": 0.0004834379979001824, "children": { "RLTrainer._checkpoint": { "total": 0.0667567880009301, "count": 1, "self": 0.0667567880009301 } } } } } } }