sgauravm's picture
Trained on colab using ML Agents
bd9d3ce verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7152026891708374,
"min": 0.7102195024490356,
"max": 2.8414807319641113,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6797.2861328125,
"min": 6797.2861328125,
"max": 29005.8359375,
"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": 12.998610496520996,
"min": 0.4489198625087738,
"max": 12.998610496520996,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.72900390625,
"min": 87.0904541015625,
"max": 2638.3349609375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07266243738601641,
"min": 0.06269461955896843,
"max": 0.07421367743832068,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29064974954406564,
"min": 0.25077847823587374,
"max": 0.3673770781868941,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19335050661774242,
"min": 0.14765469877816298,
"max": 0.2965897257421531,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7734020264709697,
"min": 0.5906187951126519,
"max": 1.4829486287107654,
"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": 25.681818181818183,
"min": 3.909090909090909,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 172.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.909090909090909,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 172.0,
"max": 1411.0,
"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": "1743247172",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743247609"
},
"total": 436.99776788300005,
"count": 1,
"self": 0.49574619700001676,
"children": {
"run_training.setup": {
"total": 0.03372091400001409,
"count": 1,
"self": 0.03372091400001409
},
"TrainerController.start_learning": {
"total": 436.468300772,
"count": 1,
"self": 0.3685075399764628,
"children": {
"TrainerController._reset_env": {
"total": 3.045355560999951,
"count": 1,
"self": 3.045355560999951
},
"TrainerController.advance": {
"total": 432.94797230302356,
"count": 18192,
"self": 0.3733487980287009,
"children": {
"env_step": {
"total": 308.26825313100153,
"count": 18192,
"self": 234.09781209497282,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.95167841702369,
"count": 18192,
"self": 1.3235368040320736,
"children": {
"TorchPolicy.evaluate": {
"total": 72.62814161299161,
"count": 18192,
"self": 72.62814161299161
}
}
},
"workers": {
"total": 0.2187626190050196,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 434.8628829650156,
"count": 18192,
"is_parallel": true,
"self": 229.5655038480088,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005365051999888237,
"count": 1,
"is_parallel": true,
"self": 0.0036762490001365222,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001688802999751715,
"count": 10,
"is_parallel": true,
"self": 0.001688802999751715
}
}
},
"UnityEnvironment.step": {
"total": 0.03958745400018415,
"count": 1,
"is_parallel": true,
"self": 0.0006302160002178425,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040792499999042775,
"count": 1,
"is_parallel": true,
"self": 0.00040792499999042775
},
"communicator.exchange": {
"total": 0.03645821400004934,
"count": 1,
"is_parallel": true,
"self": 0.03645821400004934
},
"steps_from_proto": {
"total": 0.002091098999926544,
"count": 1,
"is_parallel": true,
"self": 0.00038664599969706615,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017044530002294778,
"count": 10,
"is_parallel": true,
"self": 0.0017044530002294778
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.2973791170068,
"count": 18191,
"is_parallel": true,
"self": 9.817224716013925,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.407064310984424,
"count": 18191,
"is_parallel": true,
"self": 5.407064310984424
},
"communicator.exchange": {
"total": 158.0728105039973,
"count": 18191,
"is_parallel": true,
"self": 158.0728105039973
},
"steps_from_proto": {
"total": 32.000279586011175,
"count": 18191,
"is_parallel": true,
"self": 5.829433178962745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.17084640704843,
"count": 181910,
"is_parallel": true,
"self": 26.17084640704843
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.30637037399333,
"count": 18192,
"self": 0.46486592702171947,
"children": {
"process_trajectory": {
"total": 27.211461777971635,
"count": 18192,
"self": 26.618008293971116,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5934534840005199,
"count": 4,
"self": 0.5934534840005199
}
}
},
"_update_policy": {
"total": 96.63004266899998,
"count": 90,
"self": 38.88230408400932,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.74773858499066,
"count": 4587,
"self": 57.74773858499066
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.209999577957205e-07,
"count": 1,
"self": 8.209999577957205e-07
},
"TrainerController._save_models": {
"total": 0.1064645470000869,
"count": 1,
"self": 0.0009413230000063777,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10552322400008052,
"count": 1,
"self": 0.10552322400008052
}
}
}
}
}
}
}