hung3r's picture
First training of SnowballTarget
820c624 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9705256819725037,
"min": 0.9705256819725037,
"max": 2.8746261596679688,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9266.5791015625,
"min": 9266.5791015625,
"max": 29470.66796875,
"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": 12.947646141052246,
"min": 0.4860164225101471,
"max": 12.947646141052246,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.791015625,
"min": 94.28718566894531,
"max": 2612.42822265625,
"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": 0.06723327946725903,
"min": 0.06406365376360733,
"max": 0.07491310260393577,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2689331178690361,
"min": 0.2562546150544293,
"max": 0.35995643549055484,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20640110538578502,
"min": 0.1141576683924844,
"max": 0.288345146354507,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8256044215431401,
"min": 0.4566306735699376,
"max": 1.441725731772535,
"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.CumulativeReward.mean": {
"value": 25.545454545454547,
"min": 3.6136363636363638,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 159.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.6136363636363638,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 159.0,
"max": 1405.0,
"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": "1757837382",
"python_version": "3.10.18 (main, Sep 2 2025, 14:19:37) [Clang 20.1.4 ]",
"command_line_arguments": "/home/kali/HFRLCourse/unit5/.venv/bin/mlagents-learn ../SnowballTarget.yaml --env=../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+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1757837633"
},
"total": 251.87474234,
"count": 1,
"self": 0.22004368099987914,
"children": {
"run_training.setup": {
"total": 0.012155100999734714,
"count": 1,
"self": 0.012155100999734714
},
"TrainerController.start_learning": {
"total": 251.6425435580004,
"count": 1,
"self": 0.24834320310037583,
"children": {
"TrainerController._reset_env": {
"total": 2.367199618000086,
"count": 1,
"self": 2.367199618000086
},
"TrainerController.advance": {
"total": 248.9921818048997,
"count": 18201,
"self": 0.12363293187627278,
"children": {
"env_step": {
"total": 248.86854887302343,
"count": 18201,
"self": 201.9184774760888,
"children": {
"SubprocessEnvManager._take_step": {
"total": 46.834679882988894,
"count": 18201,
"self": 0.5686023709649817,
"children": {
"TorchPolicy.evaluate": {
"total": 46.26607751202391,
"count": 18201,
"self": 46.26607751202391
}
}
},
"workers": {
"total": 0.115391513945724,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 251.06723450295885,
"count": 18201,
"is_parallel": true,
"self": 83.4565416159985,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020116979994782014,
"count": 1,
"is_parallel": true,
"self": 0.0009369989993501804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001074699000128021,
"count": 10,
"is_parallel": true,
"self": 0.001074699000128021
}
}
},
"UnityEnvironment.step": {
"total": 0.025471399000707606,
"count": 1,
"is_parallel": true,
"self": 0.00016214599963859655,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001674980003372184,
"count": 1,
"is_parallel": true,
"self": 0.0001674980003372184
},
"communicator.exchange": {
"total": 0.023384220000480127,
"count": 1,
"is_parallel": true,
"self": 0.023384220000480127
},
"steps_from_proto": {
"total": 0.0017575350002516643,
"count": 1,
"is_parallel": true,
"self": 0.00016193800092878519,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015955969993228791,
"count": 10,
"is_parallel": true,
"self": 0.0015955969993228791
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 167.61069288696035,
"count": 18200,
"is_parallel": true,
"self": 2.803753636935653,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.0083163549898018,
"count": 18200,
"is_parallel": true,
"self": 2.0083163549898018
},
"communicator.exchange": {
"total": 154.5125377820359,
"count": 18200,
"is_parallel": true,
"self": 154.5125377820359
},
"steps_from_proto": {
"total": 8.28608511299899,
"count": 18200,
"is_parallel": true,
"self": 1.693863925018377,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.592221187980613,
"count": 182000,
"is_parallel": true,
"self": 6.592221187980613
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.648599992331583e-05,
"count": 1,
"self": 6.648599992331583e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 246.8741997418865,
"count": 423519,
"is_parallel": true,
"self": 5.8201573060487135,
"children": {
"process_trajectory": {
"total": 145.55324159384054,
"count": 423519,
"is_parallel": true,
"self": 145.27447069284153,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2787709009990067,
"count": 4,
"is_parallel": true,
"self": 0.2787709009990067
}
}
},
"_update_policy": {
"total": 95.50080084199726,
"count": 90,
"is_parallel": true,
"self": 17.400528027011205,
"children": {
"TorchPPOOptimizer.update": {
"total": 78.10027281498606,
"count": 4587,
"is_parallel": true,
"self": 78.10027281498606
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.034752446000311465,
"count": 1,
"self": 0.0014254450006774277,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03332700099963404,
"count": 1,
"self": 0.03332700099963404
}
}
}
}
}
}
}