LizardAPN's picture
Fist model for Snowball Target
fa6f143 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8162352442741394,
"min": 0.8162352442741394,
"max": 2.8438892364501953,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7757.49951171875,
"min": 7757.49951171875,
"max": 29030.421875,
"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": 13.1535005569458,
"min": 0.47492024302482605,
"max": 13.1535005569458,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2564.9326171875,
"min": 92.13452911376953,
"max": 2645.60546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06867397391447322,
"min": 0.06239034926656327,
"max": 0.07545244586927925,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2746958956578929,
"min": 0.25926555121344896,
"max": 0.37726222934639625,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1990314057352496,
"min": 0.15130420555885626,
"max": 0.28461708204419006,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7961256229409984,
"min": 0.6052168222354251,
"max": 1.4230854102209503,
"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": 26.545454545454547,
"min": 4.136363636363637,
"max": 26.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1168.0,
"min": 182.0,
"max": 1435.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.545454545454547,
"min": 4.136363636363637,
"max": 26.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1168.0,
"min": 182.0,
"max": 1435.0,
"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": "1754992644",
"python_version": "3.10.12 (main, Aug 12 2025, 15:10:59) [GCC 13.3.0]",
"command_line_arguments": "/home/dmin/.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",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1754993226"
},
"total": 579.5286113409966,
"count": 1,
"self": 0.27008343997295015,
"children": {
"run_training.setup": {
"total": 0.022725600021658465,
"count": 1,
"self": 0.022725600021658465
},
"TrainerController.start_learning": {
"total": 579.235802301002,
"count": 1,
"self": 0.36313339247135445,
"children": {
"TrainerController._reset_env": {
"total": 3.2740268830093555,
"count": 1,
"self": 3.2740268830093555
},
"TrainerController.advance": {
"total": 575.5056678845431,
"count": 18192,
"self": 0.3538532067614142,
"children": {
"env_step": {
"total": 379.1724848479498,
"count": 18192,
"self": 226.46241986687528,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.49570970749483,
"count": 18192,
"self": 1.5325994406302925,
"children": {
"TorchPolicy.evaluate": {
"total": 150.96311026686453,
"count": 18192,
"self": 150.96311026686453
}
}
},
"workers": {
"total": 0.21435527357971296,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 578.1432323980553,
"count": 18192,
"is_parallel": true,
"self": 375.49471212673234,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002895293990150094,
"count": 1,
"is_parallel": true,
"self": 0.0016660939436405897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012292000465095043,
"count": 10,
"is_parallel": true,
"self": 0.0012292000465095043
}
}
},
"UnityEnvironment.step": {
"total": 0.023899264982901514,
"count": 1,
"is_parallel": true,
"self": 0.0002100460114888847,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015317698125727475,
"count": 1,
"is_parallel": true,
"self": 0.00015317698125727475
},
"communicator.exchange": {
"total": 0.022688650991767645,
"count": 1,
"is_parallel": true,
"self": 0.022688650991767645
},
"steps_from_proto": {
"total": 0.0008473909983877093,
"count": 1,
"is_parallel": true,
"self": 0.0001769350201357156,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006704559782519937,
"count": 10,
"is_parallel": true,
"self": 0.0006704559782519937
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.64852027132292,
"count": 18191,
"is_parallel": true,
"self": 4.124392374156741,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.633082566258963,
"count": 18191,
"is_parallel": true,
"self": 2.633082566258963
},
"communicator.exchange": {
"total": 183.81802128170966,
"count": 18191,
"is_parallel": true,
"self": 183.81802128170966
},
"steps_from_proto": {
"total": 12.073024049197556,
"count": 18191,
"is_parallel": true,
"self": 2.8226432879455388,
"children": {
"_process_rank_one_or_two_observation": {
"total": 9.250380761252018,
"count": 181910,
"is_parallel": true,
"self": 9.250380761252018
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 195.97932982983184,
"count": 18192,
"self": 0.43520804081344977,
"children": {
"process_trajectory": {
"total": 36.09977951989276,
"count": 18192,
"self": 35.571070160891395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5287093590013683,
"count": 4,
"self": 0.5287093590013683
}
}
},
"_update_policy": {
"total": 159.44434226912563,
"count": 90,
"self": 21.959213508700486,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.48512876042514,
"count": 4587,
"self": 137.48512876042514
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.099871825426817e-07,
"count": 1,
"self": 6.099871825426817e-07
},
"TrainerController._save_models": {
"total": 0.09297353099100292,
"count": 1,
"self": 0.0010473089932929724,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09192622199770994,
"count": 1,
"self": 0.09192622199770994
}
}
}
}
}
}
}