{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.913129985332489, "min": 0.9080080389976501, "max": 2.873220920562744, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8768.787109375, "min": 8768.787109375, "max": 29424.654296875, "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": 12.840019226074219, "min": 0.41193681955337524, "max": 12.840019226074219, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2503.8037109375, "min": 79.91574096679688, "max": 2589.074951171875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0687519599972703, "min": 0.062378743229726065, "max": 0.07649290990130063, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2750078399890812, "min": 0.2585884623010369, "max": 0.35926593363161796, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2036801660319279, "min": 0.13796223106556663, "max": 0.29245029411771717, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8147206641277116, "min": 0.5518489242622665, "max": 1.4430803752997343, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.106097298000005e-06, "min": 8.106097298000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.242438919200002e-05, "min": 3.242438919200002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10270200000000002, "min": 0.10270200000000002, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41080800000000006, "min": 0.41080800000000006, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014482980000000007, "min": 0.00014482980000000007, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005793192000000003, "min": 0.0005793192000000003, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.59090909090909, "min": 3.75, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 165.0, "max": 1396.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.75, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 165.0, "max": 1396.0, "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": "1745672508", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745673074" }, "total": 565.8566154150001, "count": 1, "self": 0.7901869490001445, "children": { "run_training.setup": { "total": 0.030112029000008533, "count": 1, "self": 0.030112029000008533 }, "TrainerController.start_learning": { "total": 565.036316437, "count": 1, "self": 0.8212102879978147, "children": { "TrainerController._reset_env": { "total": 3.358132722999983, "count": 1, "self": 3.358132722999983 }, "TrainerController.advance": { "total": 560.7304436780022, "count": 18212, "self": 0.4294967570126573, "children": { "env_step": { "total": 560.3009469209895, "count": 18212, "self": 435.28572716998303, "children": { "SubprocessEnvManager._take_step": { "total": 124.62982105700115, "count": 18212, "self": 2.1596025170005646, "children": { "TorchPolicy.evaluate": { "total": 122.47021854000059, "count": 18212, "self": 122.47021854000059 } } }, "workers": { "total": 0.385398694005346, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 563.073597310999, "count": 18212, "is_parallel": true, "self": 262.3505873259937, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00545289399997273, "count": 1, "is_parallel": true, "self": 0.0037396759999523965, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017132180000203334, "count": 10, "is_parallel": true, "self": 0.0017132180000203334 } } }, "UnityEnvironment.step": { "total": 0.04219550400000571, "count": 1, "is_parallel": true, "self": 0.000688867000008031, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000459567000007155, "count": 1, "is_parallel": true, "self": 0.000459567000007155 }, "communicator.exchange": { "total": 0.038888290999977926, "count": 1, "is_parallel": true, "self": 0.038888290999977926 }, "steps_from_proto": { "total": 0.0021587790000126006, "count": 1, "is_parallel": true, "self": 0.00044466500008866205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017141139999239385, "count": 10, "is_parallel": true, "self": 0.0017141139999239385 } } } } } } }, "UnityEnvironment.step": { "total": 300.7230099850054, "count": 18211, "is_parallel": true, "self": 13.467348653010788, "children": { "UnityEnvironment._generate_step_input": { "total": 7.10533244499868, "count": 18211, "is_parallel": true, "self": 7.10533244499868 }, "communicator.exchange": { "total": 238.17790721600164, "count": 18211, "is_parallel": true, "self": 238.17790721600164 }, "steps_from_proto": { "total": 41.972421670994265, "count": 18211, "is_parallel": true, "self": 8.328902483987918, "children": { "_process_rank_one_or_two_observation": { "total": 33.64351918700635, "count": 182110, "is_parallel": true, "self": 33.64351918700635 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0030549059999884776, "count": 1, "self": 0.0030549059999884776, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 554.5276080729752, "count": 751679, "is_parallel": true, "self": 15.835573209977838, "children": { "process_trajectory": { "total": 297.98634689799724, "count": 751679, "is_parallel": true, "self": 296.84267766799724, "children": { "RLTrainer._checkpoint": { "total": 1.1436692300000004, "count": 4, "is_parallel": true, "self": 1.1436692300000004 } } }, "_update_policy": { "total": 240.7056879650001, "count": 90, "is_parallel": true, "self": 63.88762971500461, "children": { "TorchPPOOptimizer.update": { "total": 176.8180582499955, "count": 4584, "is_parallel": true, "self": 176.8180582499955 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12347484199995051, "count": 1, "self": 0.0013711779999994178, "children": { "RLTrainer._checkpoint": { "total": 0.1221036639999511, "count": 1, "self": 0.1221036639999511 } } } } } } }