{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5326029062271118, "min": 0.5227048397064209, "max": 0.9090038537979126, "count": 80 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5061.85791015625, "min": 4967.78662109375, "max": 9239.115234375, "count": 80 }, "SnowballTarget.Step.mean": { "value": 999992.0, "min": 209936.0, "max": 999992.0, "count": 80 }, "SnowballTarget.Step.sum": { "value": 999992.0, "min": 209936.0, "max": 999992.0, "count": 80 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.173223495483398, "min": 13.16577434539795, "max": 14.405982971191406, "count": 80 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2763.778564453125, "min": 2567.235595703125, "max": 2953.2265625, "count": 80 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 80 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 80 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06899481696722004, "min": 0.06391147776853091, "max": 0.0725305397531723, "count": 80 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27597926786888016, "min": 0.26089074859860645, "max": 0.3626526987658615, "count": 80 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14936638727565021, "min": 0.13474033800337243, "max": 0.20730669712921718, "count": 80 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5974655491026009, "min": 0.5846467292593682, "max": 1.0152903094011196, "count": 80 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.4028995324000038e-06, "min": 1.4028995324000038e-06, "max": 0.0002383428205524, "count": 80 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.611598129600015e-06, "min": 5.611598129600015e-06, "max": 0.001176864107712, "count": 80 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10046760000000002, "min": 0.10046760000000002, "max": 0.17944760000000004, "count": 80 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40187040000000007, "min": 0.40187040000000007, "max": 0.8922880000000001, "count": 80 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.3333240000000065e-05, "min": 3.3333240000000065e-05, "max": 0.003974435239999999, "count": 80 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00013333296000000026, "min": 0.00013333296000000026, "max": 0.0196251712, "count": 80 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.863636363636363, "min": 25.10909090909091, "max": 28.381818181818183, "count": 80 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1226.0, "min": 1108.0, "max": 1561.0, "count": 80 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.863636363636363, "min": 25.10909090909091, "max": 28.381818181818183, "count": 80 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1226.0, "min": 1108.0, "max": 1561.0, "count": 80 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726854827", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726857174" }, "total": 2346.2864499879997, "count": 1, "self": 0.4358599130005132, "children": { "run_training.setup": { "total": 0.07445213099981629, "count": 1, "self": 0.07445213099981629 }, "TrainerController.start_learning": { "total": 2345.7761379439994, "count": 1, "self": 2.251796450945676, "children": { "TrainerController._reset_env": { "total": 2.3781630909998057, "count": 1, "self": 2.3781630909998057 }, "TrainerController.advance": { "total": 2341.061490449054, "count": 72736, "self": 1.0147861170685246, "children": { "env_step": { "total": 2340.0467043319854, "count": 72736, "self": 1657.531445365043, "children": { "SubprocessEnvManager._take_step": { "total": 681.2458301628749, "count": 72736, "self": 5.593772210789666, "children": { "TorchPolicy.evaluate": { "total": 675.6520579520852, "count": 72736, "self": 675.6520579520852 } } }, "workers": { "total": 1.269428804067502, "count": 72736, "self": 0.0, "children": { "worker_root": { "total": 2341.6077854111395, "count": 72736, "is_parallel": true, "self": 1505.3031205361635, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030896049997863884, "count": 1, "is_parallel": true, "self": 0.0008106050004244025, "children": { "_process_rank_one_or_two_observation": { "total": 0.002278999999361986, "count": 10, "is_parallel": true, "self": 0.002278999999361986 } } }, "UnityEnvironment.step": { "total": 0.05363281099971573, "count": 1, "is_parallel": true, "self": 0.0006811249995735125, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004004070001428772, "count": 1, "is_parallel": true, "self": 0.0004004070001428772 }, "communicator.exchange": { "total": 0.04846765399997821, "count": 1, "is_parallel": true, "self": 0.04846765399997821 }, "steps_from_proto": { "total": 0.004083625000021129, "count": 1, "is_parallel": true, "self": 0.0003947330001210503, "children": { "_process_rank_one_or_two_observation": { "total": 0.003688891999900079, "count": 10, "is_parallel": true, "self": 0.003688891999900079 } } } } } } }, "UnityEnvironment.step": { "total": 836.304664874976, "count": 72735, "is_parallel": true, "self": 38.80943300871513, "children": { "UnityEnvironment._generate_step_input": { "total": 20.712948599077208, "count": 72735, "is_parallel": true, "self": 20.712948599077208 }, "communicator.exchange": { "total": 651.1329285991415, "count": 72735, "is_parallel": true, "self": 651.1329285991415 }, "steps_from_proto": { "total": 125.64935466804218, "count": 72735, "is_parallel": true, "self": 23.57902727997498, "children": { "_process_rank_one_or_two_observation": { "total": 102.0703273880672, "count": 727350, "is_parallel": true, "self": 102.0703273880672 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001593429997228668, "count": 1, "self": 0.0001593429997228668, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2318.9619156790004, "count": 2749667, "is_parallel": true, "self": 57.1321107081294, "children": { "process_trajectory": { "total": 954.4814090508658, "count": 2749667, "is_parallel": true, "self": 952.0762051158654, "children": { "RLTrainer._checkpoint": { "total": 2.4052039350003724, "count": 16, "is_parallel": true, "self": 2.4052039350003724 } } }, "_update_policy": { "total": 1307.3483959200053, "count": 363, "is_parallel": true, "self": 508.36442521995286, "children": { "TorchPPOOptimizer.update": { "total": 798.9839707000524, "count": 49360, "is_parallel": true, "self": 798.9839707000524 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08452861000023404, "count": 1, "self": 0.001199008000185131, "children": { "RLTrainer._checkpoint": { "total": 0.08332960200004891, "count": 1, "self": 0.08332960200004891 } } } } } } }