{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.79984050989151, "min": 0.79984050989151, "max": 2.8636891841888428, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7636.876953125, "min": 7636.876953125, "max": 29390.04296875, "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": 12.74717903137207, "min": 0.33841487765312195, "max": 12.74717903137207, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2485.699951171875, "min": 65.6524887084961, "max": 2583.771484375, "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": 0.06805893188963333, "min": 0.06161286963569913, "max": 0.07754965329978743, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2722357275585333, "min": 0.24645147854279653, "max": 0.3877482664989371, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20492399892970625, "min": 0.11713304019683754, "max": 0.2836487629980433, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.819695995718825, "min": 0.46853216078735016, "max": 1.4004580840906677, "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": 25.386363636363637, "min": 3.0, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 132.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.0, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 132.0, "max": 1388.0, "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": "1699349397", "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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699349778" }, "total": 381.6161183879999, "count": 1, "self": 0.4334244540000327, "children": { "run_training.setup": { "total": 0.03958878899993579, "count": 1, "self": 0.03958878899993579 }, "TrainerController.start_learning": { "total": 381.14310514499994, "count": 1, "self": 0.5766226649921009, "children": { "TrainerController._reset_env": { "total": 0.8002962040000057, "count": 1, "self": 0.8002962040000057 }, "TrainerController.advance": { "total": 379.7065868270083, "count": 18200, "self": 0.2837908580004296, "children": { "env_step": { "total": 379.4227959690079, "count": 18200, "self": 296.6351749239375, "children": { "SubprocessEnvManager._take_step": { "total": 82.37826636203681, "count": 18200, "self": 1.268191909064626, "children": { "TorchPolicy.evaluate": { "total": 81.11007445297219, "count": 18200, "self": 81.11007445297219 } } }, "workers": { "total": 0.4093546830335981, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 380.0770244110572, "count": 18200, "is_parallel": true, "self": 159.91524219209805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015555409995613445, "count": 1, "is_parallel": true, "self": 0.0003600229993026005, "children": { "_process_rank_one_or_two_observation": { "total": 0.001195518000258744, "count": 10, "is_parallel": true, "self": 0.001195518000258744 } } }, "UnityEnvironment.step": { "total": 0.030114588999822445, "count": 1, "is_parallel": true, "self": 0.0004945000000589062, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003430699998716591, "count": 1, "is_parallel": true, "self": 0.0003430699998716591 }, "communicator.exchange": { "total": 0.02773112900013075, "count": 1, "is_parallel": true, "self": 0.02773112900013075 }, "steps_from_proto": { "total": 0.0015458899997611297, "count": 1, "is_parallel": true, "self": 0.00030708999975104234, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012388000000100874, "count": 10, "is_parallel": true, "self": 0.0012388000000100874 } } } } } } }, "UnityEnvironment.step": { "total": 220.16178221895916, "count": 18199, "is_parallel": true, "self": 8.80121705201509, "children": { "UnityEnvironment._generate_step_input": { "total": 5.22758422102288, "count": 18199, "is_parallel": true, "self": 5.22758422102288 }, "communicator.exchange": { "total": 177.37214505596876, "count": 18199, "is_parallel": true, "self": 177.37214505596876 }, "steps_from_proto": { "total": 28.760835889952432, "count": 18199, "is_parallel": true, "self": 5.628736822942301, "children": { "_process_rank_one_or_two_observation": { "total": 23.13209906701013, "count": 181990, "is_parallel": true, "self": 23.13209906701013 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00038570899960177485, "count": 1, "self": 0.00038570899960177485, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 376.7488000910771, "count": 431865, "is_parallel": true, "self": 7.867518565124556, "children": { "process_trajectory": { "total": 215.23516756395247, "count": 431865, "is_parallel": true, "self": 214.80835397295323, "children": { "RLTrainer._checkpoint": { "total": 0.4268135909992452, "count": 4, "is_parallel": true, "self": 0.4268135909992452 } } }, "_update_policy": { "total": 153.64611396200007, "count": 90, "is_parallel": true, "self": 44.58889974500789, "children": { "TorchPPOOptimizer.update": { "total": 109.05721421699218, "count": 4584, "is_parallel": true, "self": 109.05721421699218 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05921373999990465, "count": 1, "self": 0.0008984599999166676, "children": { "RLTrainer._checkpoint": { "total": 0.05831527999998798, "count": 1, "self": 0.05831527999998798 } } } } } } }