{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.5123602151870728, "min": 1.5123602151870728, "max": 2.511146068572998, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 75460.7265625, "min": 75460.7265625, "max": 126843.015625, "count": 2 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 49936.0, "max": 99960.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 49936.0, "max": 99960.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.18249225616455, "min": 2.643481731414795, "max": 8.18249225616455, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 8207.0400390625, "min": 2622.333984375, "max": 8207.0400390625, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09871511047774234, "min": 0.09871511047774234, "max": 0.09917394726748223, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 2.2704475409880738, "min": 2.181826839884609, "max": 2.2704475409880738, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.25111746017877506, "min": 0.2151398170731464, "max": 0.25111746017877506, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 5.775701584111826, "min": 4.73307597560922, "max": 5.775701584111826, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.586407471199998e-05, "min": 7.586407471199998e-05, "max": 0.000224364025212, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0017448737183759996, "min": 0.0017448737183759996, "max": 0.004936008554664, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12528800000000004, "min": 0.12528800000000004, "max": 0.17478800000000003, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 2.881624000000001, "min": 2.881624000000001, "max": 3.8453360000000005, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0012718712000000004, "min": 0.0012718712000000004, "max": 0.0037419212000000006, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.02925303760000001, "min": 0.02925303760000001, "max": 0.08232226640000001, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 50347.0, "min": 48158.0, "max": 50347.0, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 18.529644268774703, "min": 8.900826446280991, "max": 18.529644268774703, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 4688.0, "min": 2154.0, "max": 4688.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 18.529644268774703, "min": 8.900826446280991, "max": 18.529644268774703, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 4688.0, "min": 2154.0, "max": 4688.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742361505", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742361752" }, "total": 246.37419274699982, "count": 1, "self": 0.4371809429994755, "children": { "run_training.setup": { "total": 0.030208082000172, "count": 1, "self": 0.030208082000172 }, "TrainerController.start_learning": { "total": 245.90680372200018, "count": 1, "self": 0.19060375400931662, "children": { "TrainerController._reset_env": { "total": 3.546072181999989, "count": 1, "self": 3.546072181999989 }, "TrainerController.advance": { "total": 242.02379815199106, "count": 9128, "self": 0.19975880597371543, "children": { "env_step": { "total": 155.76883814001212, "count": 9128, "self": 119.11546028900034, "children": { "SubprocessEnvManager._take_step": { "total": 36.540397569004654, "count": 9128, "self": 0.6683223180093592, "children": { "TorchPolicy.evaluate": { "total": 35.872075250995294, "count": 9128, "self": 35.872075250995294 } } }, "workers": { "total": 0.11298028200712906, "count": 9128, "self": 0.0, "children": { "worker_root": { "total": 245.1219800699971, "count": 9128, "is_parallel": true, "self": 140.77382164201435, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0115638620000027, "count": 1, "is_parallel": true, "self": 0.009935203000168258, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016286589998344425, "count": 10, "is_parallel": true, "self": 0.0016286589998344425 } } }, "UnityEnvironment.step": { "total": 0.0616096109999944, "count": 1, "is_parallel": true, "self": 0.0006192929999997432, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003930200000468176, "count": 1, "is_parallel": true, "self": 0.0003930200000468176 }, "communicator.exchange": { "total": 0.05839838399992914, "count": 1, "is_parallel": true, "self": 0.05839838399992914 }, "steps_from_proto": { "total": 0.0021989140000187035, "count": 1, "is_parallel": true, "self": 0.00040621999983159185, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017926940001871117, "count": 10, "is_parallel": true, "self": 0.0017926940001871117 } } } } } } }, "UnityEnvironment.step": { "total": 104.34815842798275, "count": 9127, "is_parallel": true, "self": 4.9314935399945625, "children": { "UnityEnvironment._generate_step_input": { "total": 2.810366086003114, "count": 9127, "is_parallel": true, "self": 2.810366086003114 }, "communicator.exchange": { "total": 80.14472444199487, "count": 9127, "is_parallel": true, "self": 80.14472444199487 }, "steps_from_proto": { "total": 16.46157435999021, "count": 9127, "is_parallel": true, "self": 3.0001101129687413, "children": { "_process_rank_one_or_two_observation": { "total": 13.461464247021468, "count": 91270, "is_parallel": true, "self": 13.461464247021468 } } } } } } } } } } }, "trainer_advance": { "total": 86.05520120600522, "count": 9128, "self": 0.2293240229987532, "children": { "process_trajectory": { "total": 13.414073752006288, "count": 9128, "self": 13.414073752006288 }, "_update_policy": { "total": 72.41180343100018, "count": 45, "self": 20.189881863986102, "children": { "TorchPPOOptimizer.update": { "total": 52.22192156701408, "count": 4587, "self": 52.22192156701408 } } } } } } }, "trainer_threads": { "total": 9.399998361914186e-07, "count": 1, "self": 9.399998361914186e-07 }, "TrainerController._save_models": { "total": 0.14632869399997617, "count": 1, "self": 0.0006130009999196773, "children": { "RLTrainer._checkpoint": { "total": 0.1457156930000565, "count": 1, "self": 0.1457156930000565 } } } } } } }