{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8989839553833008, "min": 0.8926671147346497, "max": 2.873791217803955, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8583.4990234375, "min": 8583.4990234375, "max": 29462.107421875, "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": 13.0027494430542, "min": 0.2838077247142792, "max": 13.0027494430542, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2535.5361328125, "min": 55.05869674682617, "max": 2651.9599609375, "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.Losses.PolicyLoss.mean": { "value": 0.0682236898756659, "min": 0.06426349910964513, "max": 0.07485243668905277, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2728947595026636, "min": 0.2570539964385805, "max": 0.37426218344526385, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22072793353422016, "min": 0.1389522687075477, "max": 0.3001127037785801, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8829117341368806, "min": 0.5558090748301908, "max": 1.3958979839203405, "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.CumulativeReward.mean": { "value": 25.727272727272727, "min": 3.8181818181818183, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 168.0, "max": 1409.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.8181818181818183, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 168.0, "max": 1409.0, "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": "1697478526", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697479015" }, "total": 488.4904223340001, "count": 1, "self": 0.42758824900005266, "children": { "run_training.setup": { "total": 0.04429675200003658, "count": 1, "self": 0.04429675200003658 }, "TrainerController.start_learning": { "total": 488.018537333, "count": 1, "self": 0.5805556229914828, "children": { "TrainerController._reset_env": { "total": 7.387602178000009, "count": 1, "self": 7.387602178000009 }, "TrainerController.advance": { "total": 479.9575998230084, "count": 18200, "self": 0.28018377900622227, "children": { "env_step": { "total": 479.6774160440022, "count": 18200, "self": 328.441204559, "children": { "SubprocessEnvManager._take_step": { "total": 150.94366368399875, "count": 18200, "self": 1.597794879003061, "children": { "TorchPolicy.evaluate": { "total": 149.3458688049957, "count": 18200, "self": 149.3458688049957 } } }, "workers": { "total": 0.2925478010034226, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 486.7001861849945, "count": 18200, "is_parallel": true, "self": 235.96398038899014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005293655999992097, "count": 1, "is_parallel": true, "self": 0.0037663510000811584, "children": { "_process_rank_one_or_two_observation": { "total": 0.001527304999910939, "count": 10, "is_parallel": true, "self": 0.001527304999910939 } } }, "UnityEnvironment.step": { "total": 0.05249473099996749, "count": 1, "is_parallel": true, "self": 0.0007473569999660867, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032465200001752237, "count": 1, "is_parallel": true, "self": 0.00032465200001752237 }, "communicator.exchange": { "total": 0.049316583999996055, "count": 1, "is_parallel": true, "self": 0.049316583999996055 }, "steps_from_proto": { "total": 0.0021061379999878227, "count": 1, "is_parallel": true, "self": 0.0005382699999927354, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015678679999950873, "count": 10, "is_parallel": true, "self": 0.0015678679999950873 } } } } } } }, "UnityEnvironment.step": { "total": 250.73620579600436, "count": 18199, "is_parallel": true, "self": 10.926181783028255, "children": { "UnityEnvironment._generate_step_input": { "total": 5.760972756990043, "count": 18199, "is_parallel": true, "self": 5.760972756990043 }, "communicator.exchange": { "total": 197.76475009699084, "count": 18199, "is_parallel": true, "self": 197.76475009699084 }, "steps_from_proto": { "total": 36.28430115899522, "count": 18199, "is_parallel": true, "self": 6.98530362900641, "children": { "_process_rank_one_or_two_observation": { "total": 29.29899752998881, "count": 181990, "is_parallel": true, "self": 29.29899752998881 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014949800004160352, "count": 1, "self": 0.00014949800004160352, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.91363643394726, "count": 500474, "is_parallel": true, "self": 10.927658789978125, "children": { "process_trajectory": { "total": 270.9346155379692, "count": 500474, "is_parallel": true, "self": 270.19589846396906, "children": { "RLTrainer._checkpoint": { "total": 0.7387170740001352, "count": 4, "is_parallel": true, "self": 0.7387170740001352 } } }, "_update_policy": { "total": 194.05136210599994, "count": 90, "is_parallel": true, "self": 62.752149075998034, "children": { "TorchPPOOptimizer.update": { "total": 131.2992130300019, "count": 4587, "is_parallel": true, "self": 131.2992130300019 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09263021100002788, "count": 1, "self": 0.0008904759999950329, "children": { "RLTrainer._checkpoint": { "total": 0.09173973500003285, "count": 1, "self": 0.09173973500003285 } } } } } } }