Stilt34's picture
Initial Commit.
5d65402 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.4074875116348267,
"min": 1.4074875116348267,
"max": 2.887389659881592,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13376.76171875,
"min": 13376.76171875,
"max": 29474.47265625,
"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": 9.673080444335938,
"min": 0.36353182792663574,
"max": 9.673080444335938,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1886.2506103515625,
"min": 70.52517700195312,
"max": 1959.8121337890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06846193643272558,
"min": 0.06138092412446021,
"max": 0.07250432125988929,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2738477457309023,
"min": 0.24552369649784084,
"max": 0.36163786128528563,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.26347837903920346,
"min": 0.09768494061084793,
"max": 0.28071714230612216,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0539135161568138,
"min": 0.3907397624433917,
"max": 1.4035857115306107,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.6940973060000025e-06,
"min": 2.6940973060000025e-06,
"max": 9.729400270599998e-05,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.077638922400001e-05,
"min": 1.077638922400001e-05,
"max": 0.0004617200382800001,
"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": 19.09090909090909,
"min": 2.772727272727273,
"max": 19.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 840.0,
"min": 122.0,
"max": 1033.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 19.09090909090909,
"min": 2.772727272727273,
"max": 19.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 840.0,
"min": 122.0,
"max": 1033.0,
"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": "1778084296",
"python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]",
"command_line_arguments": "/content/mlagents_venv/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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1778084753"
},
"total": 457.56419744100003,
"count": 1,
"self": 0.4860809319998225,
"children": {
"run_training.setup": {
"total": 0.024391007000303944,
"count": 1,
"self": 0.024391007000303944
},
"TrainerController.start_learning": {
"total": 457.0537255019999,
"count": 1,
"self": 0.42255380297683587,
"children": {
"TrainerController._reset_env": {
"total": 3.1757441920003657,
"count": 1,
"self": 3.1757441920003657
},
"TrainerController.advance": {
"total": 453.3748569210229,
"count": 18192,
"self": 0.39681422903686325,
"children": {
"env_step": {
"total": 331.1290900260242,
"count": 18192,
"self": 256.9324309510889,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.95245787199065,
"count": 18192,
"self": 1.3448156250374268,
"children": {
"TorchPolicy.evaluate": {
"total": 72.60764224695322,
"count": 18192,
"self": 72.60764224695322
}
}
},
"workers": {
"total": 0.24420120294462322,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.1989792620161,
"count": 18192,
"is_parallel": true,
"self": 229.9009069869967,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004890533999969193,
"count": 1,
"is_parallel": true,
"self": 0.0031831390006118454,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017073949993573478,
"count": 10,
"is_parallel": true,
"self": 0.0017073949993573478
}
}
},
"UnityEnvironment.step": {
"total": 0.03488786199977767,
"count": 1,
"is_parallel": true,
"self": 0.0005873059994883079,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003870390000884072,
"count": 1,
"is_parallel": true,
"self": 0.0003870390000884072
},
"communicator.exchange": {
"total": 0.03192034699986834,
"count": 1,
"is_parallel": true,
"self": 0.03192034699986834
},
"steps_from_proto": {
"total": 0.0019931700003326114,
"count": 1,
"is_parallel": true,
"self": 0.00037224200013952213,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016209280001930892,
"count": 10,
"is_parallel": true,
"self": 0.0016209280001930892
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.29807227501942,
"count": 18191,
"is_parallel": true,
"self": 10.545109969988971,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.816375006012549,
"count": 18191,
"is_parallel": true,
"self": 5.816375006012549
},
"communicator.exchange": {
"total": 170.1417582700028,
"count": 18191,
"is_parallel": true,
"self": 170.1417582700028
},
"steps_from_proto": {
"total": 38.79482902901509,
"count": 18191,
"is_parallel": true,
"self": 6.887036217021887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.907792811993204,
"count": 181910,
"is_parallel": true,
"self": 31.907792811993204
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.84895266596186,
"count": 18192,
"self": 0.4690674929670422,
"children": {
"process_trajectory": {
"total": 27.00708726199582,
"count": 18192,
"self": 26.581170798996027,
"children": {
"RLTrainer._checkpoint": {
"total": 0.425916462999794,
"count": 4,
"self": 0.425916462999794
}
}
},
"_update_policy": {
"total": 94.372797910999,
"count": 90,
"self": 37.917272970992144,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.45552494000685,
"count": 4587,
"self": 56.45552494000685
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.72999714576872e-07,
"count": 1,
"self": 9.72999714576872e-07
},
"TrainerController._save_models": {
"total": 0.0805696130000797,
"count": 1,
"self": 0.0007101599999259633,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07985945300015374,
"count": 1,
"self": 0.07985945300015374
}
}
}
}
}
}
}