Misklean's picture
First Push
4cc93a1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.319703459739685,
"min": 1.319703459739685,
"max": 2.886234760284424,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13471.533203125,
"min": 12762.6005859375,
"max": 31484.36328125,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.039812088012695,
"min": 0.2253216803073883,
"max": 13.039812088012695,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1303.981201171875,
"min": 21.856203079223633,
"max": 1303.981201171875,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.94,
"min": 3.090909090909091,
"max": 26.387755102040817,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1297.0,
"min": 136.0,
"max": 1373.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.94,
"min": 3.090909090909091,
"max": 26.387755102040817,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1297.0,
"min": 136.0,
"max": 1373.0,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04896519445755984,
"min": 0.04221622802570517,
"max": 0.055580709635058366,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.14689558337267952,
"min": 0.08443245605141034,
"max": 0.15977164205465028,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19032208262120975,
"min": 0.10857257106724907,
"max": 0.2987783190082101,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5709662478636293,
"min": 0.21714514213449815,
"max": 0.7778067995520199,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.7334316000000015e-06,
"min": 1.7334316000000015e-06,
"max": 9.780000220000002e-05,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.200294800000005e-06,
"min": 5.200294800000005e-06,
"max": 0.00026480003520000007,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.29999999999999993,
"min": 0.19999999999999996,
"max": 0.29999999999999993,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.716000000000002e-05,
"min": 2.716000000000002e-05,
"max": 0.0009782200000000001,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 8.148000000000007e-05,
"min": 8.148000000000007e-05,
"max": 0.0026515200000000005,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1729016524",
"python_version": "3.10.12 (main, Oct 15 2024, 18:54:33) [GCC 13.2.0]",
"command_line_arguments": "/home/floflo/Documents/projects/rl_lesson/rl-venv3.10.12/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729016956"
},
"total": 432.41586207,
"count": 1,
"self": 0.2214334480013349,
"children": {
"run_training.setup": {
"total": 0.017229664998012595,
"count": 1,
"self": 0.017229664998012595
},
"TrainerController.start_learning": {
"total": 432.17719895700066,
"count": 1,
"self": 0.4981280669126136,
"children": {
"TrainerController._reset_env": {
"total": 1.1270095070030948,
"count": 1,
"self": 1.1270095070030948
},
"TrainerController.advance": {
"total": 430.4349442270832,
"count": 27328,
"self": 0.516263162746327,
"children": {
"env_step": {
"total": 278.29279240010874,
"count": 27328,
"self": 197.34595857243403,
"children": {
"SubprocessEnvManager._take_step": {
"total": 80.64146436774536,
"count": 27328,
"self": 1.2817206002182502,
"children": {
"TorchPolicy.evaluate": {
"total": 79.3597437675271,
"count": 27328,
"self": 79.3597437675271
}
}
},
"workers": {
"total": 0.30536945992935216,
"count": 27328,
"self": 0.0,
"children": {
"worker_root": {
"total": 431.2487377665602,
"count": 27328,
"is_parallel": true,
"self": 264.1675334114698,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001536364001367474,
"count": 1,
"is_parallel": true,
"self": 0.00034525101000326686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011911129913642071,
"count": 10,
"is_parallel": true,
"self": 0.0011911129913642071
}
}
},
"UnityEnvironment.step": {
"total": 0.016315422999468865,
"count": 1,
"is_parallel": true,
"self": 0.0003473840006336104,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002677949996723328,
"count": 1,
"is_parallel": true,
"self": 0.0002677949996723328
},
"communicator.exchange": {
"total": 0.01479861599727883,
"count": 1,
"is_parallel": true,
"self": 0.01479861599727883
},
"steps_from_proto": {
"total": 0.0009016280018840916,
"count": 1,
"is_parallel": true,
"self": 0.00018840600387193263,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000713221998012159,
"count": 10,
"is_parallel": true,
"self": 0.000713221998012159
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 167.08120435509045,
"count": 27327,
"is_parallel": true,
"self": 7.38497305744022,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.557532685765182,
"count": 27327,
"is_parallel": true,
"self": 5.557532685765182
},
"communicator.exchange": {
"total": 130.75430571090692,
"count": 27327,
"is_parallel": true,
"self": 130.75430571090692
},
"steps_from_proto": {
"total": 23.384392900978128,
"count": 27327,
"is_parallel": true,
"self": 4.7455681315477705,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.638824769430357,
"count": 273270,
"is_parallel": true,
"self": 18.638824769430357
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 151.6258886642281,
"count": 27328,
"self": 0.7061429219829733,
"children": {
"process_trajectory": {
"total": 28.46861323324265,
"count": 27328,
"self": 27.70197600224128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7666372310013685,
"count": 6,
"self": 0.7666372310013685
}
}
},
"_update_policy": {
"total": 122.45113250900249,
"count": 68,
"self": 69.80464342601772,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.64648908298477,
"count": 5780,
"self": 52.64648908298477
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.310001481324434e-07,
"count": 1,
"self": 6.310001481324434e-07
},
"TrainerController._save_models": {
"total": 0.11711652500162018,
"count": 1,
"self": 0.0026941629985230975,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11442236200309708,
"count": 1,
"self": 0.11442236200309708
}
}
}
}
}
}
}