duydl's picture
First Push
b420a56 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8386112451553345,
"min": 0.8386112451553345,
"max": 2.8538668155670166,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7970.1611328125,
"min": 7970.1611328125,
"max": 29132.271484375,
"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": 12.118337631225586,
"min": 0.40022018551826477,
"max": 12.142048835754395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2363.075927734375,
"min": 77.64271545410156,
"max": 2476.97802734375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06996670207373944,
"min": 0.06270735491210978,
"max": 0.07820655910843782,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27986680829495775,
"min": 0.25242511706778265,
"max": 0.37223368655623723,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18245836069770888,
"min": 0.1242891670725144,
"max": 0.2959380542530733,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7298334427908355,
"min": 0.4971566682900576,
"max": 1.4796902712653663,
"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": 23.295454545454547,
"min": 3.3181818181818183,
"max": 24.12727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1025.0,
"min": 146.0,
"max": 1327.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.295454545454547,
"min": 3.3181818181818183,
"max": 24.12727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1025.0,
"min": 146.0,
"max": 1327.0,
"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": "1751752591",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/mnt/Work/Projects/huggingface/deep-rl-class/.pixi/envs/default/bin/mlagents-learn /mnt/Work/Projects/huggingface/deep-rl-class/notebooks/unit5/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget4 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751753211"
},
"total": 619.4893544229999,
"count": 1,
"self": 0.4236702600173885,
"children": {
"run_training.setup": {
"total": 0.0345963559957454,
"count": 1,
"self": 0.0345963559957454
},
"TrainerController.start_learning": {
"total": 619.0310878069868,
"count": 1,
"self": 0.4028439381363569,
"children": {
"TrainerController._reset_env": {
"total": 5.815171623995411,
"count": 1,
"self": 5.815171623995411
},
"TrainerController.advance": {
"total": 612.7228279158444,
"count": 18192,
"self": 0.3738644476106856,
"children": {
"env_step": {
"total": 453.4824337233731,
"count": 18192,
"self": 360.95075972538325,
"children": {
"SubprocessEnvManager._take_step": {
"total": 92.28918389881437,
"count": 18192,
"self": 1.2082838333008112,
"children": {
"TorchPolicy.evaluate": {
"total": 91.08090006551356,
"count": 18192,
"self": 91.08090006551356
}
}
},
"workers": {
"total": 0.24249009917548392,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 617.8075386831915,
"count": 18192,
"is_parallel": true,
"self": 289.04928204929456,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003628522012149915,
"count": 1,
"is_parallel": true,
"self": 0.001004747042316012,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002623774969833903,
"count": 10,
"is_parallel": true,
"self": 0.002623774969833903
}
}
},
"UnityEnvironment.step": {
"total": 0.035248692001914605,
"count": 1,
"is_parallel": true,
"self": 0.0008160149882314727,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005539359990507364,
"count": 1,
"is_parallel": true,
"self": 0.0005539359990507364
},
"communicator.exchange": {
"total": 0.031143535001319833,
"count": 1,
"is_parallel": true,
"self": 0.031143535001319833
},
"steps_from_proto": {
"total": 0.0027352060133125633,
"count": 1,
"is_parallel": true,
"self": 0.0005798750062240288,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021553310070885345,
"count": 10,
"is_parallel": true,
"self": 0.0021553310070885345
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 328.75825663389696,
"count": 18191,
"is_parallel": true,
"self": 13.511991627077805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.101998004771303,
"count": 18191,
"is_parallel": true,
"self": 8.101998004771303
},
"communicator.exchange": {
"total": 263.5346406081662,
"count": 18191,
"is_parallel": true,
"self": 263.5346406081662
},
"steps_from_proto": {
"total": 43.609626393881626,
"count": 18191,
"is_parallel": true,
"self": 8.821014445638866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.78861194824276,
"count": 181910,
"is_parallel": true,
"self": 34.78861194824276
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 158.8665297448606,
"count": 18192,
"self": 0.49527709490212146,
"children": {
"process_trajectory": {
"total": 33.28226178501791,
"count": 18192,
"self": 32.87295376800466,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40930801701324526,
"count": 4,
"self": 0.40930801701324526
}
}
},
"_update_policy": {
"total": 125.08899086494057,
"count": 90,
"self": 38.57594676522422,
"children": {
"TorchPPOOptimizer.update": {
"total": 86.51304409971635,
"count": 4587,
"self": 86.51304409971635
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.390059858560562e-07,
"count": 1,
"self": 9.390059858560562e-07
},
"TrainerController._save_models": {
"total": 0.09024339000461623,
"count": 1,
"self": 0.0007517580088460818,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08949163199577015,
"count": 1,
"self": 0.08949163199577015
}
}
}
}
}
}
}