Tass-k's picture
First Push
3400b2d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.079757571220398,
"min": 1.079757571220398,
"max": 2.8382720947265625,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10262.015625,
"min": 10262.015625,
"max": 28973.08203125,
"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": 12.722766876220703,
"min": 0.35542604327201843,
"max": 12.722766876220703,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2480.939453125,
"min": 68.95265197753906,
"max": 2565.45947265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07105394233247567,
"min": 0.05967735971538715,
"max": 0.07517198850583358,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28421576932990267,
"min": 0.2387094388615486,
"max": 0.3758599425291679,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19720825246151755,
"min": 0.1181580446427688,
"max": 0.2972569351687151,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7888330098460702,
"min": 0.4726321785710752,
"max": 1.3352413256378735,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"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.Environment.CumulativeReward.mean": {
"value": 25.386363636363637,
"min": 3.1363636363636362,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 138.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.1363636363636362,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 138.0,
"max": 1379.0,
"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": "1774286627",
"python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"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": "1774287031"
},
"total": 403.88308770899994,
"count": 1,
"self": 0.37829542800000127,
"children": {
"run_training.setup": {
"total": 0.027584618999981103,
"count": 1,
"self": 0.027584618999981103
},
"TrainerController.start_learning": {
"total": 403.47720766199996,
"count": 1,
"self": 0.5217686779990345,
"children": {
"TrainerController._reset_env": {
"total": 3.2078459089998432,
"count": 1,
"self": 3.2078459089998432
},
"TrainerController.advance": {
"total": 399.69815761200107,
"count": 18192,
"self": 0.4790166369691633,
"children": {
"env_step": {
"total": 293.6993515520194,
"count": 18192,
"self": 251.85746373499887,
"children": {
"SubprocessEnvManager._take_step": {
"total": 41.52071138600354,
"count": 18192,
"self": 1.2812721999807763,
"children": {
"TorchPolicy.evaluate": {
"total": 40.239439186022764,
"count": 18192,
"self": 40.239439186022764
}
}
},
"workers": {
"total": 0.3211764310169656,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 401.75973519699505,
"count": 18192,
"is_parallel": true,
"self": 184.71140740398414,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004966329000126279,
"count": 1,
"is_parallel": true,
"self": 0.003934169000103793,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010321600000224862,
"count": 10,
"is_parallel": true,
"self": 0.0010321600000224862
}
}
},
"UnityEnvironment.step": {
"total": 0.03749625900013598,
"count": 1,
"is_parallel": true,
"self": 0.0005072590001873323,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004409299999679206,
"count": 1,
"is_parallel": true,
"self": 0.0004409299999679206
},
"communicator.exchange": {
"total": 0.034825740000087535,
"count": 1,
"is_parallel": true,
"self": 0.034825740000087535
},
"steps_from_proto": {
"total": 0.0017223299998931907,
"count": 1,
"is_parallel": true,
"self": 0.0003066499998567451,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014156800000364456,
"count": 10,
"is_parallel": true,
"self": 0.0014156800000364456
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.0483277930109,
"count": 18191,
"is_parallel": true,
"self": 10.139761845957082,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.973114948018974,
"count": 18191,
"is_parallel": true,
"self": 5.973114948018974
},
"communicator.exchange": {
"total": 168.87599873501358,
"count": 18191,
"is_parallel": true,
"self": 168.87599873501358
},
"steps_from_proto": {
"total": 32.059452264021274,
"count": 18191,
"is_parallel": true,
"self": 6.545749779998687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.513702484022588,
"count": 181910,
"is_parallel": true,
"self": 25.513702484022588
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 105.51978942301253,
"count": 18192,
"self": 0.6731813969977338,
"children": {
"process_trajectory": {
"total": 21.21684322101487,
"count": 18192,
"self": 20.9251568690147,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2916863520001698,
"count": 4,
"self": 0.2916863520001698
}
}
},
"_update_policy": {
"total": 83.62976480499992,
"count": 90,
"self": 33.14025832099742,
"children": {
"TorchPPOOptimizer.update": {
"total": 50.489506484002504,
"count": 4587,
"self": 50.489506484002504
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.90999978967011e-07,
"count": 1,
"self": 9.90999978967011e-07
},
"TrainerController._save_models": {
"total": 0.04943447200002993,
"count": 1,
"self": 0.0006588199998986966,
"children": {
"RLTrainer._checkpoint": {
"total": 0.04877565200013123,
"count": 1,
"self": 0.04877565200013123
}
}
}
}
}
}
}