Lpremier's picture
Push snowball target agent.
da61732 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8976149559020996,
"min": 0.8976149559020996,
"max": 2.8547418117523193,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8560.5537109375,
"min": 8560.5537109375,
"max": 29266.8125,
"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": 12.660547256469727,
"min": 0.41191866993904114,
"max": 12.660547256469727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.806640625,
"min": 79.91222381591797,
"max": 2544.3779296875,
"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": 0.09165720405048085,
"min": 0.09165720405048085,
"max": 0.10358789673459708,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3666288162019234,
"min": 0.3666288162019234,
"max": 0.5116555356302449,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20294827852836425,
"min": 0.14125627707452051,
"max": 0.2693033568634122,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.811793114113457,
"min": 0.5650251082980821,
"max": 1.2552711011147968,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0776097306000009e-05,
"min": 1.0776097306000009e-05,
"max": 0.000389176002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.3104389224000035e-05,
"min": 4.3104389224000035e-05,
"max": 0.0018468800382799998,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999997,
"min": 0.10269399999999997,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077599999999986,
"min": 0.41077599999999986,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.90909090909091,
"min": 4.045454545454546,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1096.0,
"min": 178.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.90909090909091,
"min": 4.045454545454546,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1096.0,
"min": 178.0,
"max": 1400.0,
"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": "1737304092",
"python_version": "3.11.2 (main, Sep 14 2024, 03:00:30) [GCC 12.2.0]",
"command_line_arguments": "/home/lucien/Workspace/deep-rl-hugging-face/.venv/bin/mlagents-learn ./SnowballTarget.yaml --env=./envs/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1737304799"
},
"total": 706.8909784760035,
"count": 1,
"self": 0.26962345000356436,
"children": {
"run_training.setup": {
"total": 0.02011503199901199,
"count": 1,
"self": 0.02011503199901199
},
"TrainerController.start_learning": {
"total": 706.6012399940009,
"count": 1,
"self": 0.37414307390281465,
"children": {
"TrainerController._reset_env": {
"total": 1.677723895998497,
"count": 1,
"self": 1.677723895998497
},
"TrainerController.advance": {
"total": 704.5050866051024,
"count": 18198,
"self": 0.1568069246277446,
"children": {
"env_step": {
"total": 704.3482796804747,
"count": 18198,
"self": 644.2469872947768,
"children": {
"SubprocessEnvManager._take_step": {
"total": 59.92476509616972,
"count": 18198,
"self": 1.1925463584120735,
"children": {
"TorchPolicy.evaluate": {
"total": 58.73221873775765,
"count": 18198,
"self": 58.73221873775765
}
}
},
"workers": {
"total": 0.17652728952816688,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 705.9761597883626,
"count": 18198,
"is_parallel": true,
"self": 111.35898568942503,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003883290999510791,
"count": 1,
"is_parallel": true,
"self": 0.0017035850032698363,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002179705996240955,
"count": 10,
"is_parallel": true,
"self": 0.002179705996240955
}
}
},
"UnityEnvironment.step": {
"total": 0.038991988003544975,
"count": 1,
"is_parallel": true,
"self": 0.00023713300470262766,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006132269991212524,
"count": 1,
"is_parallel": true,
"self": 0.0006132269991212524
},
"communicator.exchange": {
"total": 0.03710080200107768,
"count": 1,
"is_parallel": true,
"self": 0.03710080200107768
},
"steps_from_proto": {
"total": 0.0010408259986434132,
"count": 1,
"is_parallel": true,
"self": 0.00025774197274586186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007830840258975513,
"count": 10,
"is_parallel": true,
"self": 0.0007830840258975513
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 594.6171740989375,
"count": 18197,
"is_parallel": true,
"self": 2.9881041999251465,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.108184457283642,
"count": 18197,
"is_parallel": true,
"self": 11.108184457283642
},
"communicator.exchange": {
"total": 562.525170782319,
"count": 18197,
"is_parallel": true,
"self": 562.525170782319
},
"steps_from_proto": {
"total": 17.995714659409714,
"count": 18197,
"is_parallel": true,
"self": 3.2049943277961574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 14.790720331613556,
"count": 181970,
"is_parallel": true,
"self": 14.790720331613556
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.545599611243233e-05,
"count": 1,
"self": 3.545599611243233e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 699.9891338078014,
"count": 1328633,
"is_parallel": true,
"self": 12.312986813209136,
"children": {
"process_trajectory": {
"total": 428.9367974096458,
"count": 1328633,
"is_parallel": true,
"self": 428.54743002865143,
"children": {
"RLTrainer._checkpoint": {
"total": 0.38936738099437207,
"count": 4,
"is_parallel": true,
"self": 0.38936738099437207
}
}
},
"_update_policy": {
"total": 258.73934958494647,
"count": 90,
"is_parallel": true,
"self": 29.37461268689367,
"children": {
"TorchPPOOptimizer.update": {
"total": 229.3647368980528,
"count": 9177,
"is_parallel": true,
"self": 229.3647368980528
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.04425096300110454,
"count": 1,
"self": 0.0005689629979315214,
"children": {
"RLTrainer._checkpoint": {
"total": 0.043682000003173016,
"count": 1,
"self": 0.043682000003173016
}
}
}
}
}
}
}