sErial03's picture
Increase max_steps to 2e6
ddad63b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7701504230499268,
"min": 0.7656258344650269,
"max": 2.890308141708374,
"count": 140
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7929.46875,
"min": 7396.3359375,
"max": 29528.98046875,
"count": 140
},
"SnowballTarget.Step.mean": {
"value": 1399968.0,
"min": 9952.0,
"max": 1399968.0,
"count": 140
},
"SnowballTarget.Step.sum": {
"value": 1399968.0,
"min": 9952.0,
"max": 1399968.0,
"count": 140
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.166781425476074,
"min": -0.12361296266317368,
"max": 14.166781425476074,
"count": 140
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2890.0234375,
"min": -23.980915069580078,
"max": 2890.0234375,
"count": 140
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 140
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 140
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.581818181818182,
"min": 2.7045454545454546,
"max": 28.4,
"count": 140
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1517.0,
"min": 119.0,
"max": 1562.0,
"count": 140
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.581818181818182,
"min": 2.7045454545454546,
"max": 28.4,
"count": 140
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1517.0,
"min": 119.0,
"max": 1562.0,
"count": 140
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 140
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 140
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03238388441783923,
"min": 0.027749783229955936,
"max": 0.04213238783995621,
"count": 133
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.03238388441783923,
"min": 0.027749783229955936,
"max": 0.04213238783995621,
"count": 133
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15203782301100474,
"min": 0.08559608033725194,
"max": 0.31449879159530003,
"count": 133
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.15203782301100474,
"min": 0.08559608033725194,
"max": 0.31449879159530003,
"count": 133
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 9.145326951559998e-05,
"min": 9.145326951559998e-05,
"max": 0.00029836320054560004,
"count": 133
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 9.145326951559998e-05,
"min": 9.145326951559998e-05,
"max": 0.00029836320054560004,
"count": 133
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.13048440000000006,
"min": 0.13048440000000006,
"max": 0.19945440000000006,
"count": 133
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.13048440000000006,
"min": 0.13048440000000006,
"max": 0.19945440000000006,
"count": 133
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0015311715600000006,
"min": 0.0015311715600000006,
"max": 0.0049727745600000005,
"count": 133
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0015311715600000006,
"min": 0.0015311715600000006,
"max": 0.0049727745600000005,
"count": 133
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1735828441",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1735831086"
},
"total": 2645.0431771169997,
"count": 1,
"self": 0.2702252909998606,
"children": {
"run_training.setup": {
"total": 0.056339447000027576,
"count": 1,
"self": 0.056339447000027576
},
"TrainerController.start_learning": {
"total": 2644.716612379,
"count": 1,
"self": 2.357972935955786,
"children": {
"TrainerController._reset_env": {
"total": 2.0717897399999856,
"count": 1,
"self": 2.0717897399999856
},
"TrainerController.advance": {
"total": 2640.130034937044,
"count": 127410,
"self": 2.4775885128533446,
"children": {
"env_step": {
"total": 2035.083508942159,
"count": 127410,
"self": 1551.4433312870374,
"children": {
"SubprocessEnvManager._take_step": {
"total": 482.1545468320578,
"count": 127410,
"self": 8.463040096167788,
"children": {
"TorchPolicy.evaluate": {
"total": 473.69150673589,
"count": 127410,
"self": 473.69150673589
}
}
},
"workers": {
"total": 1.4856308230637296,
"count": 127409,
"self": 0.0,
"children": {
"worker_root": {
"total": 2637.2616070511426,
"count": 127409,
"is_parallel": true,
"self": 1275.1481269522542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023126549999687995,
"count": 1,
"is_parallel": true,
"self": 0.0007755520000500837,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015371029999187158,
"count": 10,
"is_parallel": true,
"self": 0.0015371029999187158
}
}
},
"UnityEnvironment.step": {
"total": 0.048304481000286614,
"count": 1,
"is_parallel": true,
"self": 0.0006531300005008234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003851729998132214,
"count": 1,
"is_parallel": true,
"self": 0.0003851729998132214
},
"communicator.exchange": {
"total": 0.045396382000035373,
"count": 1,
"is_parallel": true,
"self": 0.045396382000035373
},
"steps_from_proto": {
"total": 0.001869795999937196,
"count": 1,
"is_parallel": true,
"self": 0.00036458299928199267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015052130006552034,
"count": 10,
"is_parallel": true,
"self": 0.0015052130006552034
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1362.1134800988884,
"count": 127408,
"is_parallel": true,
"self": 69.0470171870029,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 38.201372316096695,
"count": 127408,
"is_parallel": true,
"self": 38.201372316096695
},
"communicator.exchange": {
"total": 1036.73148657187,
"count": 127408,
"is_parallel": true,
"self": 1036.73148657187
},
"steps_from_proto": {
"total": 218.1336040239189,
"count": 127408,
"is_parallel": true,
"self": 38.394573956658405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 179.7390300672605,
"count": 1274080,
"is_parallel": true,
"self": 179.7390300672605
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 602.5689374820317,
"count": 127409,
"self": 2.6347049030027847,
"children": {
"process_trajectory": {
"total": 190.8393916780292,
"count": 127409,
"self": 188.12887053103032,
"children": {
"RLTrainer._checkpoint": {
"total": 2.7105211469988717,
"count": 28,
"self": 2.7105211469988717
}
}
},
"_update_policy": {
"total": 409.09484090099977,
"count": 134,
"self": 285.5651750940451,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.52966580695465,
"count": 8142,
"self": 123.52966580695465
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2780001270584762e-06,
"count": 1,
"self": 1.2780001270584762e-06
},
"TrainerController._save_models": {
"total": 0.15681348799989792,
"count": 1,
"self": 0.0012386159996822244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1555748720002157,
"count": 1,
"self": 0.1555748720002157
}
}
}
}
}
}
}