mattbailey1991's picture
Trained model
5fb7609 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7496972680091858,
"min": 0.7496972680091858,
"max": 2.824309825897217,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7125.12255859375,
"min": 7125.12255859375,
"max": 28830.5546875,
"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": 12.131518363952637,
"min": 0.3833796977996826,
"max": 12.131518363952637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2365.64599609375,
"min": 74.37566375732422,
"max": 2423.1103515625,
"count": 20
},
"SnowballTarget.Policy.CuriosityValueEstimate.mean": {
"value": 0.00878231879323721,
"min": 0.006468311417847872,
"max": 0.06444625556468964,
"count": 20
},
"SnowballTarget.Policy.CuriosityValueEstimate.sum": {
"value": 1.7125521898269653,
"min": 1.2548524141311646,
"max": 12.50257396697998,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06903499019715717,
"min": 0.060146103617429905,
"max": 0.07526220253157412,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2761399607886287,
"min": 0.24058441446971962,
"max": 0.3763110126578706,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.11994049818638493,
"min": 0.0656326178166851,
"max": 0.12932833831976442,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.4797619927455397,
"min": 0.2625304712667404,
"max": 0.6270918546646249,
"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.Losses.CuriosityForwardLoss.mean": {
"value": 0.04883155591931997,
"min": 0.04883155591931997,
"max": 0.22953225137191074,
"count": 20
},
"SnowballTarget.Losses.CuriosityForwardLoss.sum": {
"value": 0.1953262236772799,
"min": 0.1953262236772799,
"max": 0.918129005487643,
"count": 20
},
"SnowballTarget.Losses.CuriosityInverseLoss.mean": {
"value": 0.6754336631765553,
"min": 0.6677401204903921,
"max": 2.841785842954528,
"count": 20
},
"SnowballTarget.Losses.CuriosityInverseLoss.sum": {
"value": 2.701734652706221,
"min": 2.701734652706221,
"max": 12.398786465326946,
"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": 24.15909090909091,
"min": 3.6136363636363638,
"max": 24.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1063.0,
"min": 159.0,
"max": 1309.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.15909090909091,
"min": 3.6136363636363638,
"max": 24.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1063.0,
"min": 159.0,
"max": 1309.0,
"count": 20
},
"SnowballTarget.Policy.CuriosityReward.mean": {
"value": 0.009836434279846302,
"min": 0.009836434279846302,
"max": 0.02654828665188027,
"count": 20
},
"SnowballTarget.Policy.CuriosityReward.sum": {
"value": 0.4328031083132373,
"min": 0.4328031083132373,
"max": 1.1681246126827318,
"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": "1743946323",
"python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]",
"command_line_arguments": "/home/mbailey91/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --torch-device cuda:0 --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": "2.6.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1743946829"
},
"total": 505.0951869659475,
"count": 1,
"self": 0.6248495229519904,
"children": {
"run_training.setup": {
"total": 0.046296485990751535,
"count": 1,
"self": 0.046296485990751535
},
"TrainerController.start_learning": {
"total": 504.42404095700476,
"count": 1,
"self": 0.31594557146308944,
"children": {
"TrainerController._reset_env": {
"total": 4.077565214014612,
"count": 1,
"self": 4.077565214014612
},
"TrainerController.advance": {
"total": 499.87081842153566,
"count": 18192,
"self": 0.30788406130159274,
"children": {
"env_step": {
"total": 292.41188450146,
"count": 18192,
"self": 207.22839898761595,
"children": {
"SubprocessEnvManager._take_step": {
"total": 84.98590090946527,
"count": 18192,
"self": 0.9314500298933126,
"children": {
"TorchPolicy.evaluate": {
"total": 84.05445087957196,
"count": 18192,
"self": 84.05445087957196
}
}
},
"workers": {
"total": 0.19758460437878966,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 503.3704033375252,
"count": 18192,
"is_parallel": true,
"self": 315.6436232398264,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016578850336372852,
"count": 1,
"is_parallel": true,
"self": 0.00048489501932635903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011729900143109262,
"count": 10,
"is_parallel": true,
"self": 0.0011729900143109262
}
}
},
"UnityEnvironment.step": {
"total": 0.021418806980364025,
"count": 1,
"is_parallel": true,
"self": 0.00024419697001576424,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001800990430638194,
"count": 1,
"is_parallel": true,
"self": 0.0001800990430638194
},
"communicator.exchange": {
"total": 0.020226317981723696,
"count": 1,
"is_parallel": true,
"self": 0.020226317981723696
},
"steps_from_proto": {
"total": 0.000768192985560745,
"count": 1,
"is_parallel": true,
"self": 0.00020099803805351257,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005671949475072324,
"count": 10,
"is_parallel": true,
"self": 0.0005671949475072324
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 187.7267800976988,
"count": 18191,
"is_parallel": true,
"self": 4.045139730849769,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.516080104804132,
"count": 18191,
"is_parallel": true,
"self": 2.516080104804132
},
"communicator.exchange": {
"total": 167.39187312638387,
"count": 18191,
"is_parallel": true,
"self": 167.39187312638387
},
"steps_from_proto": {
"total": 13.77368713566102,
"count": 18191,
"is_parallel": true,
"self": 3.36501373257488,
"children": {
"_process_rank_one_or_two_observation": {
"total": 10.40867340308614,
"count": 181910,
"is_parallel": true,
"self": 10.40867340308614
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 207.15104985877406,
"count": 18192,
"self": 0.4136917153955437,
"children": {
"process_trajectory": {
"total": 43.43703851825558,
"count": 18192,
"self": 42.818663396232296,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6183751220232807,
"count": 4,
"self": 0.6183751220232807
}
}
},
"_update_policy": {
"total": 163.30031962512294,
"count": 90,
"self": 88.46222586807562,
"children": {
"TorchPPOOptimizer.update": {
"total": 74.83809375704732,
"count": 4587,
"self": 74.83809375704732
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.00000761449337e-06,
"count": 1,
"self": 1.00000761449337e-06
},
"TrainerController._save_models": {
"total": 0.15971074998378754,
"count": 1,
"self": 0.01476656598970294,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1449441839940846,
"count": 1,
"self": 0.1449441839940846
}
}
}
}
}
}
}