{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.4679950773715973, "min": 0.38374993205070496, "max": 0.6615180373191833, "count": 60 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4447.8251953125, "min": 3812.37939453125, "max": 6752.7763671875, "count": 60 }, "SnowballTarget.Step.mean": { "value": 999968.0, "min": 409984.0, "max": 999968.0, "count": 60 }, "SnowballTarget.Step.sum": { "value": 999968.0, "min": 409984.0, "max": 999968.0, "count": 60 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.876036643981934, "min": 13.391283988952637, "max": 13.960137367248535, "count": 60 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2705.8271484375, "min": 2601.3369140625, "max": 2861.828125, "count": 60 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06618709982870438, "min": 0.05818265929915736, "max": 0.07400698466340591, "count": 60 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26474839931481753, "min": 0.23273063719662945, "max": 0.37003492331702953, "count": 60 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16579554620765002, "min": 0.1497262521409521, "max": 0.20163759180143764, "count": 60 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6631821848306001, "min": 0.6237345821425027, "max": 1.0081879590071883, "count": 60 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.4292995235999971e-06, "min": 1.4292995235999971e-06, "max": 0.00017830924056360002, "count": 60 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.717198094399989e-06, "min": 5.717198094399989e-06, "max": 0.000876696207768, "count": 60 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1004764, "min": 0.1004764, "max": 0.1594364, "count": 60 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4019056, "min": 0.4019056, "max": 0.7922319999999999, "count": 60 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.377235999999996e-05, "min": 3.377235999999996e-05, "max": 0.00297587636, "count": 60 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00013508943999999983, "min": 0.00013508943999999983, "max": 0.014632376800000003, "count": 60 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 60 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 60 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.431818181818183, "min": 25.818181818181817, "max": 27.454545454545453, "count": 60 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1207.0, "min": 1136.0, "max": 1506.0, "count": 60 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.431818181818183, "min": 25.818181818181817, "max": 27.454545454545453, "count": 60 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1207.0, "min": 1136.0, "max": 1506.0, "count": 60 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1756992169", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756993425" }, "total": 1256.160303181, "count": 1, "self": 0.43472935699992377, "children": { "run_training.setup": { "total": 0.023579695000080392, "count": 1, "self": 0.023579695000080392 }, "TrainerController.start_learning": { "total": 1255.701994129, "count": 1, "self": 1.1253022049859283, "children": { "TrainerController._reset_env": { "total": 2.4907634189999044, "count": 1, "self": 2.4907634189999044 }, "TrainerController.advance": { "total": 1252.0077177970143, "count": 54528, "self": 1.1258705890163583, "children": { "env_step": { "total": 894.0392946919515, "count": 54528, "self": 689.9123704620029, "children": { "SubprocessEnvManager._take_step": { "total": 203.40392476400257, "count": 54528, "self": 3.7421630480198473, "children": { "TorchPolicy.evaluate": { "total": 199.66176171598272, "count": 54528, "self": 199.66176171598272 } } }, "workers": { "total": 0.7229994659460317, "count": 54528, "self": 0.0, "children": { "worker_root": { "total": 1252.1318862160356, "count": 54528, "is_parallel": true, "self": 646.2807679570305, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021272920002957107, "count": 1, "is_parallel": true, "self": 0.0006649699998888536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014623220004068571, "count": 10, "is_parallel": true, "self": 0.0014623220004068571 } } }, "UnityEnvironment.step": { "total": 0.07391307799980495, "count": 1, "is_parallel": true, "self": 0.0005864249992555415, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004106380001758225, "count": 1, "is_parallel": true, "self": 0.0004106380001758225 }, "communicator.exchange": { "total": 0.0709302610002851, "count": 1, "is_parallel": true, "self": 0.0709302610002851 }, "steps_from_proto": { "total": 0.001985754000088491, "count": 1, "is_parallel": true, "self": 0.0005044510007792269, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014813029993092641, "count": 10, "is_parallel": true, "self": 0.0014813029993092641 } } } } } } }, "UnityEnvironment.step": { "total": 605.851118259005, "count": 54527, "is_parallel": true, "self": 28.509037880080996, "children": { "UnityEnvironment._generate_step_input": { "total": 15.722490518978702, "count": 54527, "is_parallel": true, "self": 15.722490518978702 }, "communicator.exchange": { "total": 469.76808268095874, "count": 54527, "is_parallel": true, "self": 469.76808268095874 }, "steps_from_proto": { "total": 91.8515071789866, "count": 54527, "is_parallel": true, "self": 16.332675407989882, "children": { "_process_rank_one_or_two_observation": { "total": 75.51883177099671, "count": 545270, "is_parallel": true, "self": 75.51883177099671 } } } } } } } } } } }, "trainer_advance": { "total": 356.84255251604645, "count": 54528, "self": 1.3891025070342948, "children": { "process_trajectory": { "total": 75.98536393801305, "count": 54528, "self": 75.44539831201291, "children": { "RLTrainer._checkpoint": { "total": 0.5399656260001393, "count": 6, "self": 0.5399656260001393 } } }, "_update_policy": { "total": 279.4680860709991, "count": 272, "self": 113.77913209399412, "children": { "TorchPPOOptimizer.update": { "total": 165.68895397700499, "count": 13869, "self": 165.68895397700499 } } } } } } }, "trainer_threads": { "total": 1.0519997886149213e-06, "count": 1, "self": 1.0519997886149213e-06 }, "TrainerController._save_models": { "total": 0.07820965600012642, "count": 1, "self": 0.001058562000253005, "children": { "RLTrainer._checkpoint": { "total": 0.07715109399987341, "count": 1, "self": 0.07715109399987341 } } } } } } }