{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9628199338912964, "min": 0.9628199338912964, "max": 2.861560821533203, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9203.595703125, "min": 9203.595703125, "max": 29336.720703125, "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": 12.375421524047852, "min": 0.32458388805389404, "max": 12.375421524047852, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2413.207275390625, "min": 62.96927261352539, "max": 2474.7431640625, "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": 0.06758645636835033, "min": 0.06126248645716045, "max": 0.07374570427052626, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2703458254734013, "min": 0.2450499458286418, "max": 0.36872852135263134, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20510374426421726, "min": 0.12088820846139582, "max": 0.2755439681019269, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.820414977056869, "min": 0.4835528338455833, "max": 1.2980622348795625, "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": 24.65909090909091, "min": 3.5, "max": 24.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1085.0, "min": 154.0, "max": 1345.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.65909090909091, "min": 3.5, "max": 24.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1085.0, "min": 154.0, "max": 1345.0, "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": "1725986967", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725987431" }, "total": 463.672254031, "count": 1, "self": 0.4257120249999389, "children": { "run_training.setup": { "total": 0.051715738000041256, "count": 1, "self": 0.051715738000041256 }, "TrainerController.start_learning": { "total": 463.19482626800004, "count": 1, "self": 0.6059930999979883, "children": { "TrainerController._reset_env": { "total": 2.4039057100000036, "count": 1, "self": 2.4039057100000036 }, "TrainerController.advance": { "total": 460.09476485800207, "count": 18202, "self": 0.27696216500373794, "children": { "env_step": { "total": 459.8178026929983, "count": 18202, "self": 285.4644331730145, "children": { "SubprocessEnvManager._take_step": { "total": 174.06386217098895, "count": 18202, "self": 1.4682396799812523, "children": { "TorchPolicy.evaluate": { "total": 172.5956224910077, "count": 18202, "self": 172.5956224910077 } } }, "workers": { "total": 0.28950734899484587, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 461.96124807199743, "count": 18202, "is_parallel": true, "self": 242.06280797999602, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021628779999787184, "count": 1, "is_parallel": true, "self": 0.0006412940001041534, "children": { "_process_rank_one_or_two_observation": { "total": 0.001521583999874565, "count": 10, "is_parallel": true, "self": 0.001521583999874565 } } }, "UnityEnvironment.step": { "total": 0.034674886999994214, "count": 1, "is_parallel": true, "self": 0.0006496310001011807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042831999996906234, "count": 1, "is_parallel": true, "self": 0.00042831999996906234 }, "communicator.exchange": { "total": 0.03163721599997871, "count": 1, "is_parallel": true, "self": 0.03163721599997871 }, "steps_from_proto": { "total": 0.001959719999945264, "count": 1, "is_parallel": true, "self": 0.00039042299982838813, "children": { "_process_rank_one_or_two_observation": { "total": 0.001569297000116876, "count": 10, "is_parallel": true, "self": 0.001569297000116876 } } } } } } }, "UnityEnvironment.step": { "total": 219.8984400920014, "count": 18201, "is_parallel": true, "self": 10.055187758987643, "children": { "UnityEnvironment._generate_step_input": { "total": 5.181274606006468, "count": 18201, "is_parallel": true, "self": 5.181274606006468 }, "communicator.exchange": { "total": 172.14785497499923, "count": 18201, "is_parallel": true, "self": 172.14785497499923 }, "steps_from_proto": { "total": 32.51412275200806, "count": 18201, "is_parallel": true, "self": 6.301519093024126, "children": { "_process_rank_one_or_two_observation": { "total": 26.212603658983937, "count": 182010, "is_parallel": true, "self": 26.212603658983937 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001331839999920703, "count": 1, "self": 0.0001331839999920703, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.2687329410058, "count": 718054, "is_parallel": true, "self": 14.168502214972989, "children": { "process_trajectory": { "total": 253.72478464103273, "count": 718054, "is_parallel": true, "self": 252.88184963303274, "children": { "RLTrainer._checkpoint": { "total": 0.8429350079999836, "count": 4, "is_parallel": true, "self": 0.8429350079999836 } } }, "_update_policy": { "total": 186.37544608500008, "count": 90, "is_parallel": true, "self": 59.47531346699799, "children": { "TorchPPOOptimizer.update": { "total": 126.90013261800209, "count": 4581, "is_parallel": true, "self": 126.90013261800209 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09002941599999303, "count": 1, "self": 0.0008912219999501758, "children": { "RLTrainer._checkpoint": { "total": 0.08913819400004286, "count": 1, "self": 0.08913819400004286 } } } } } } }