SnowballTarget1 / run_logs /timers.json
aardvarkjon's picture
First attempt on the snowball game
5bb33cf verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5943527817726135,
"min": 0.5279719233512878,
"max": 2.852735757827759,
"count": 200
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6119.4560546875,
"min": 5064.306640625,
"max": 29120.7265625,
"count": 200
},
"SnowballTarget.Step.mean": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Step.sum": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.327463150024414,
"min": 0.37127000093460083,
"max": 14.467580795288086,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2937.1298828125,
"min": 72.02638244628906,
"max": 2957.28564453125,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07257504313408088,
"min": 0.05737803610470876,
"max": 0.07749372555636894,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.36287521567040437,
"min": 0.22951214441883505,
"max": 0.38746862778184465,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16326101740785676,
"min": 0.12206377234999272,
"max": 0.28435842435733943,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8163050870392837,
"min": 0.48825508939997087,
"max": 1.4217921217866971,
"count": 200
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032997656000039e-07,
"min": 7.032997656000039e-07,
"max": 0.00029918820027059994,
"count": 200
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.5164988280000196e-06,
"min": 3.5164988280000196e-06,
"max": 0.0014885160038279998,
"count": 200
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10023440000000002,
"min": 0.10023440000000002,
"max": 0.1997294,
"count": 200
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5011720000000001,
"min": 0.4029176,
"max": 0.996172,
"count": 200
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.1696560000000067e-05,
"min": 2.1696560000000067e-05,
"max": 0.004986497059999999,
"count": 200
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00010848280000000034,
"min": 0.00010848280000000034,
"max": 0.024808982800000004,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.054545454545455,
"min": 3.477272727272727,
"max": 28.933333333333334,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1543.0,
"min": 153.0,
"max": 1562.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.054545454545455,
"min": 3.477272727272727,
"max": 28.933333333333334,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1543.0,
"min": 153.0,
"max": 1562.0,
"count": 200
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1736304546",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736308868"
},
"total": 4321.889669753999,
"count": 1,
"self": 0.4254900619989712,
"children": {
"run_training.setup": {
"total": 0.05683093699997244,
"count": 1,
"self": 0.05683093699997244
},
"TrainerController.start_learning": {
"total": 4321.407348755,
"count": 1,
"self": 3.419313488919215,
"children": {
"TrainerController._reset_env": {
"total": 5.715205277999985,
"count": 1,
"self": 5.715205277999985
},
"TrainerController.advance": {
"total": 4312.18639554708,
"count": 181864,
"self": 3.6366768520047117,
"children": {
"env_step": {
"total": 3061.201997709897,
"count": 181864,
"self": 2334.9550695960484,
"children": {
"SubprocessEnvManager._take_step": {
"total": 724.0542668929507,
"count": 181864,
"self": 12.420895077841692,
"children": {
"TorchPolicy.evaluate": {
"total": 711.6333718151091,
"count": 181864,
"self": 711.6333718151091
}
}
},
"workers": {
"total": 2.192661220898003,
"count": 181864,
"self": 0.0,
"children": {
"worker_root": {
"total": 4309.599073468935,
"count": 181864,
"is_parallel": true,
"self": 2261.48784553691,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021647840000014185,
"count": 1,
"is_parallel": true,
"self": 0.0006363579998378555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001528426000163563,
"count": 10,
"is_parallel": true,
"self": 0.001528426000163563
}
}
},
"UnityEnvironment.step": {
"total": 0.03833020199999737,
"count": 1,
"is_parallel": true,
"self": 0.0007247380000308112,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045498199995108735,
"count": 1,
"is_parallel": true,
"self": 0.00045498199995108735
},
"communicator.exchange": {
"total": 0.03505268000003525,
"count": 1,
"is_parallel": true,
"self": 0.03505268000003525
},
"steps_from_proto": {
"total": 0.00209780199998022,
"count": 1,
"is_parallel": true,
"self": 0.00043491099984294124,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016628910001372788,
"count": 10,
"is_parallel": true,
"self": 0.0016628910001372788
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2048.111227932025,
"count": 181863,
"is_parallel": true,
"self": 99.92383720474663,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 55.76055485324059,
"count": 181863,
"is_parallel": true,
"self": 55.76055485324059
},
"communicator.exchange": {
"total": 1563.6107415810209,
"count": 181863,
"is_parallel": true,
"self": 1563.6107415810209
},
"steps_from_proto": {
"total": 328.8160942930168,
"count": 181863,
"is_parallel": true,
"self": 58.54834840811293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 270.2677458849039,
"count": 1818630,
"is_parallel": true,
"self": 270.2677458849039
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1247.347720985178,
"count": 181864,
"self": 4.038021611147087,
"children": {
"process_trajectory": {
"total": 285.8109068470301,
"count": 181864,
"self": 281.65456177002955,
"children": {
"RLTrainer._checkpoint": {
"total": 4.1563450770005375,
"count": 40,
"self": 4.1563450770005375
}
}
},
"_update_policy": {
"total": 957.4987925270008,
"count": 909,
"self": 393.3941151439741,
"children": {
"TorchPPOOptimizer.update": {
"total": 564.1046773830267,
"count": 46356,
"self": 564.1046773830267
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4770002962904982e-06,
"count": 1,
"self": 1.4770002962904982e-06
},
"TrainerController._save_models": {
"total": 0.08643296400077816,
"count": 1,
"self": 0.0009528190003038617,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0854801450004743,
"count": 1,
"self": 0.0854801450004743
}
}
}
}
}
}
}