addy0606's picture
First Push
ae92cd2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6766100525856018,
"min": 0.6766100525856018,
"max": 2.8672518730163574,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6430.501953125,
"min": 6430.501953125,
"max": 29268.90625,
"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": 13.051607131958008,
"min": 0.5079875588417053,
"max": 13.051607131958008,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2545.0634765625,
"min": 98.5495834350586,
"max": 2646.675537109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07033141754115659,
"min": 0.06326404697862088,
"max": 0.07930132025506408,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28132567016462634,
"min": 0.2606678918836063,
"max": 0.3590115076901081,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1750925492641388,
"min": 0.1197983138879542,
"max": 0.28191287803883647,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7003701970565552,
"min": 0.4791932555518168,
"max": 1.4095643901941823,
"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": 26.045454545454547,
"min": 3.4318181818181817,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1146.0,
"min": 151.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.045454545454547,
"min": 3.4318181818181817,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1146.0,
"min": 151.0,
"max": 1404.0,
"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": "1772860665",
"python_version": "3.10.12 (main, Jan 26 2026, 14:55:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn config/ppo/SnowballTarget.yaml --env=SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --force --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1772861113"
},
"total": 448.4964028710001,
"count": 1,
"self": 0.43390204299998913,
"children": {
"run_training.setup": {
"total": 0.03558333000000857,
"count": 1,
"self": 0.03558333000000857
},
"TrainerController.start_learning": {
"total": 448.0269174980001,
"count": 1,
"self": 0.41504797900847734,
"children": {
"TrainerController._reset_env": {
"total": 3.4747590659999332,
"count": 1,
"self": 3.4747590659999332
},
"TrainerController.advance": {
"total": 444.0588392199918,
"count": 18192,
"self": 0.42067035601507996,
"children": {
"env_step": {
"total": 320.92688809999095,
"count": 18192,
"self": 248.68865526602303,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.98311086698004,
"count": 18192,
"self": 1.305318743983662,
"children": {
"TorchPolicy.evaluate": {
"total": 70.67779212299638,
"count": 18192,
"self": 70.67779212299638
}
}
},
"workers": {
"total": 0.25512196698787193,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.30236640399494,
"count": 18192,
"is_parallel": true,
"self": 228.42457758401042,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005462821000037366,
"count": 1,
"is_parallel": true,
"self": 0.003336819000196556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021260019998408097,
"count": 10,
"is_parallel": true,
"self": 0.0021260019998408097
}
}
},
"UnityEnvironment.step": {
"total": 0.035690491999957885,
"count": 1,
"is_parallel": true,
"self": 0.0005777819997092593,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038028300014048,
"count": 1,
"is_parallel": true,
"self": 0.00038028300014048
},
"communicator.exchange": {
"total": 0.03283258100009334,
"count": 1,
"is_parallel": true,
"self": 0.03283258100009334
},
"steps_from_proto": {
"total": 0.0018998460000148043,
"count": 1,
"is_parallel": true,
"self": 0.000385488000119949,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015143579998948553,
"count": 10,
"is_parallel": true,
"self": 0.0015143579998948553
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.87778881998452,
"count": 18191,
"is_parallel": true,
"self": 9.976234734964692,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.411657347006894,
"count": 18191,
"is_parallel": true,
"self": 5.411657347006894
},
"communicator.exchange": {
"total": 166.83809114100313,
"count": 18191,
"is_parallel": true,
"self": 166.83809114100313
},
"steps_from_proto": {
"total": 35.6518055970098,
"count": 18191,
"is_parallel": true,
"self": 6.847825972981354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.803979624028443,
"count": 181910,
"is_parallel": true,
"self": 28.803979624028443
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.71128076398577,
"count": 18192,
"self": 0.499310658980221,
"children": {
"process_trajectory": {
"total": 26.85202890900632,
"count": 18192,
"self": 26.42380685700641,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42822205199991004,
"count": 4,
"self": 0.42822205199991004
}
}
},
"_update_policy": {
"total": 95.35994119599923,
"count": 90,
"self": 38.14525934100561,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.214681854993614,
"count": 4587,
"self": 57.214681854993614
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.639999578008428e-07,
"count": 1,
"self": 8.639999578008428e-07
},
"TrainerController._save_models": {
"total": 0.078270368999938,
"count": 1,
"self": 0.0007312329998967471,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07753913600004125,
"count": 1,
"self": 0.07753913600004125
}
}
}
}
}
}
}