Krazeder's picture
First Push
b900a46 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7934821248054504,
"min": 0.7934821248054504,
"max": 2.8448476791381836,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7541.25439453125,
"min": 7541.25439453125,
"max": 29040.205078125,
"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": 13.008994102478027,
"min": 0.48328930139541626,
"max": 13.008994102478027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2536.75390625,
"min": 93.75812530517578,
"max": 2606.7333984375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06771893748954622,
"min": 0.061069800475692604,
"max": 0.07588114996707351,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27087574995818486,
"min": 0.26334130035042214,
"max": 0.37940574983536757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19211062862008224,
"min": 0.12997629996229365,
"max": 0.3091065456323764,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.768442514480329,
"min": 0.5199051998491746,
"max": 1.3976071742819807,
"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": 25.818181818181817,
"min": 3.6136363636363638,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 159.0,
"max": 1420.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.6136363636363638,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 159.0,
"max": 1420.0,
"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": "1741202924",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/home/kraz/Documents/DeepRLCourse/ml-agents/VENV/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": "1741203240"
},
"total": 316.519731267,
"count": 1,
"self": 0.21854756400000497,
"children": {
"run_training.setup": {
"total": 0.014515705999997408,
"count": 1,
"self": 0.014515705999997408
},
"TrainerController.start_learning": {
"total": 316.286667997,
"count": 1,
"self": 0.23290466700666457,
"children": {
"TrainerController._reset_env": {
"total": 1.3577976359999866,
"count": 1,
"self": 1.3577976359999866
},
"TrainerController.advance": {
"total": 314.6396179529934,
"count": 18192,
"self": 0.21016536300442112,
"children": {
"env_step": {
"total": 230.35377361699898,
"count": 18192,
"self": 184.38377096000454,
"children": {
"SubprocessEnvManager._take_step": {
"total": 45.81762593000565,
"count": 18192,
"self": 0.6460696010085485,
"children": {
"TorchPolicy.evaluate": {
"total": 45.1715563289971,
"count": 18192,
"self": 45.1715563289971
}
}
},
"workers": {
"total": 0.15237672698879123,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 315.71811365200165,
"count": 18192,
"is_parallel": true,
"self": 148.36095785400425,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002069119999987379,
"count": 1,
"is_parallel": true,
"self": 0.0005337699998335665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015353500001538123,
"count": 10,
"is_parallel": true,
"self": 0.0015353500001538123
}
}
},
"UnityEnvironment.step": {
"total": 0.0185969550000209,
"count": 1,
"is_parallel": true,
"self": 0.0004692380000506091,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001701749999938329,
"count": 1,
"is_parallel": true,
"self": 0.0001701749999938329
},
"communicator.exchange": {
"total": 0.016441385999996783,
"count": 1,
"is_parallel": true,
"self": 0.016441385999996783
},
"steps_from_proto": {
"total": 0.0015161559999796737,
"count": 1,
"is_parallel": true,
"self": 0.00026688299988109065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001249273000098583,
"count": 10,
"is_parallel": true,
"self": 0.001249273000098583
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 167.3571557979974,
"count": 18191,
"is_parallel": true,
"self": 7.718558100991686,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.899016954998956,
"count": 18191,
"is_parallel": true,
"self": 3.899016954998956
},
"communicator.exchange": {
"total": 133.97401892500534,
"count": 18191,
"is_parallel": true,
"self": 133.97401892500534
},
"steps_from_proto": {
"total": 21.765561817001412,
"count": 18191,
"is_parallel": true,
"self": 3.8525805849769768,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.912981232024435,
"count": 181910,
"is_parallel": true,
"self": 17.912981232024435
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 84.07567897298998,
"count": 18192,
"self": 0.2877171819902742,
"children": {
"process_trajectory": {
"total": 16.379496916999756,
"count": 18192,
"self": 16.116984624999873,
"children": {
"RLTrainer._checkpoint": {
"total": 0.262512291999883,
"count": 4,
"self": 0.262512291999883
}
}
},
"_update_policy": {
"total": 67.40846487399995,
"count": 90,
"self": 25.747350148003648,
"children": {
"TorchPPOOptimizer.update": {
"total": 41.6611147259963,
"count": 4587,
"self": 41.6611147259963
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.919999921388808e-07,
"count": 1,
"self": 5.919999921388808e-07
},
"TrainerController._save_models": {
"total": 0.056347148999975616,
"count": 1,
"self": 0.0006831899999042435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05566395900007137,
"count": 1,
"self": 0.05566395900007137
}
}
}
}
}
}
}