{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0122157335281372, "min": 1.0082894563674927, "max": 2.876131534576416, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9664.6357421875, "min": 9664.6357421875, "max": 29454.462890625, "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": 13.08913516998291, "min": 0.4203651547431946, "max": 13.08913516998291, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2552.38134765625, "min": 81.55084228515625, "max": 2653.551025390625, "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": 0.0715785139453182, "min": 0.06378188528170166, "max": 0.0715785139453182, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2863140557812728, "min": 0.25512754112680663, "max": 0.3435025974106204, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1868015930202662, "min": 0.11240460174318001, "max": 0.30234229111788324, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7472063720810648, "min": 0.44961840697272004, "max": 1.4683283760267145, "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": 3.3181818181818183, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 146.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.3181818181818183, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 146.0, "max": 1415.0, "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": "1684742535", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684743026" }, "total": 491.7899788420001, "count": 1, "self": 0.4374750800000129, "children": { "run_training.setup": { "total": 0.06397049500003504, "count": 1, "self": 0.06397049500003504 }, "TrainerController.start_learning": { "total": 491.28853326700005, "count": 1, "self": 0.6100688919893855, "children": { "TrainerController._reset_env": { "total": 5.034369620999996, "count": 1, "self": 5.034369620999996 }, "TrainerController.advance": { "total": 485.4993414600108, "count": 18201, "self": 0.284980263010425, "children": { "env_step": { "total": 485.21436119700036, "count": 18201, "self": 351.8006376950301, "children": { "SubprocessEnvManager._take_step": { "total": 133.12564772698602, "count": 18201, "self": 1.8642575939807102, "children": { "TorchPolicy.evaluate": { "total": 131.2613901330053, "count": 18201, "self": 131.2613901330053 } } }, "workers": { "total": 0.288075774984236, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 489.544903306995, "count": 18201, "is_parallel": true, "self": 231.1890255279876, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007100781999952233, "count": 1, "is_parallel": true, "self": 0.004833934000089357, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022668479998628754, "count": 10, "is_parallel": true, "self": 0.0022668479998628754 } } }, "UnityEnvironment.step": { "total": 0.041387127999996665, "count": 1, "is_parallel": true, "self": 0.000574926999888703, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034888400000454567, "count": 1, "is_parallel": true, "self": 0.00034888400000454567 }, "communicator.exchange": { "total": 0.03823367000006783, "count": 1, "is_parallel": true, "self": 0.03823367000006783 }, "steps_from_proto": { "total": 0.002229647000035584, "count": 1, "is_parallel": true, "self": 0.0004083979999904841, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018212490000450998, "count": 10, "is_parallel": true, "self": 0.0018212490000450998 } } } } } } }, "UnityEnvironment.step": { "total": 258.3558777790074, "count": 18200, "is_parallel": true, "self": 9.947422666020884, "children": { "UnityEnvironment._generate_step_input": { "total": 5.6793805019812, "count": 18200, "is_parallel": true, "self": 5.6793805019812 }, "communicator.exchange": { "total": 206.70406111000239, "count": 18200, "is_parallel": true, "self": 206.70406111000239 }, "steps_from_proto": { "total": 36.025013501002945, "count": 18200, "is_parallel": true, "self": 7.185898043987777, "children": { "_process_rank_one_or_two_observation": { "total": 28.83911545701517, "count": 182000, "is_parallel": true, "self": 28.83911545701517 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013750699986303516, "count": 1, "self": 0.00013750699986303516, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 481.7476654041168, "count": 447688, "is_parallel": true, "self": 10.275885454194395, "children": { "process_trajectory": { "total": 268.08564454892235, "count": 447688, "is_parallel": true, "self": 254.81874023792193, "children": { "RLTrainer._checkpoint": { "total": 13.266904311000417, "count": 40, "is_parallel": true, "self": 13.266904311000417 } } }, "_update_policy": { "total": 203.38613540100005, "count": 90, "is_parallel": true, "self": 77.7706654640009, "children": { "TorchPPOOptimizer.update": { "total": 125.61546993699915, "count": 4584, "is_parallel": true, "self": 125.61546993699915 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14461578700002065, "count": 1, "self": 0.000934106000158863, "children": { "RLTrainer._checkpoint": { "total": 0.14368168099986178, "count": 1, "self": 0.14368168099986178 } } } } } } }