eLarry's picture
1st model. Trained on Colab
8959345
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0977544784545898,
"min": 1.0977544784545898,
"max": 2.8620340824127197,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10493.435546875,
"min": 10493.435546875,
"max": 29310.08984375,
"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": 12.997401237487793,
"min": 0.2724814713001251,
"max": 12.997401237487793,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.4931640625,
"min": 52.86140823364258,
"max": 2633.255126953125,
"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.Losses.PolicyLoss.mean": {
"value": 0.06574161071002177,
"min": 0.06429941573193954,
"max": 0.07479838350292423,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2629664428400871,
"min": 0.25719766292775814,
"max": 0.37035612544494534,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19701857660330976,
"min": 0.1685712490011664,
"max": 0.32229586809818794,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7880743064132391,
"min": 0.7270559539981917,
"max": 1.490419853551715,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.0002694000973060002,
"min": 0.0002694000973060002,
"max": 0.009729400002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0010776003892240009,
"min": 0.0010776003892240009,
"max": 0.04617200003828,
"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.CumulativeReward.mean": {
"value": 25.227272727272727,
"min": 2.6363636363636362,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 116.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 2.6363636363636362,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 116.0,
"max": 1409.0,
"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": "1678226506",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678227007"
},
"total": 501.60463041800006,
"count": 1,
"self": 0.38722978599992075,
"children": {
"run_training.setup": {
"total": 0.12881424400006836,
"count": 1,
"self": 0.12881424400006836
},
"TrainerController.start_learning": {
"total": 501.08858638800007,
"count": 1,
"self": 0.6799300780049862,
"children": {
"TrainerController._reset_env": {
"total": 9.898404766999988,
"count": 1,
"self": 9.898404766999988
},
"TrainerController.advance": {
"total": 490.39018166799497,
"count": 18203,
"self": 0.31262112000001707,
"children": {
"env_step": {
"total": 490.07756054799495,
"count": 18203,
"self": 338.6830096759983,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.0763532220002,
"count": 18203,
"self": 1.6777521480141786,
"children": {
"TorchPolicy.evaluate": {
"total": 149.39860107398601,
"count": 18203,
"self": 34.60709080298341,
"children": {
"TorchPolicy.sample_actions": {
"total": 114.79151027100261,
"count": 18203,
"self": 114.79151027100261
}
}
}
}
},
"workers": {
"total": 0.3181976499964776,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 499.24015133800253,
"count": 18203,
"is_parallel": true,
"self": 239.53124858598846,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0062700810000251295,
"count": 1,
"is_parallel": true,
"self": 0.004317576000289591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019525049997355381,
"count": 10,
"is_parallel": true,
"self": 0.0019525049997355381
}
}
},
"UnityEnvironment.step": {
"total": 0.03749125800004549,
"count": 1,
"is_parallel": true,
"self": 0.0004565469999988636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003540160000738979,
"count": 1,
"is_parallel": true,
"self": 0.0003540160000738979
},
"communicator.exchange": {
"total": 0.03465559799997209,
"count": 1,
"is_parallel": true,
"self": 0.03465559799997209
},
"steps_from_proto": {
"total": 0.002025097000000642,
"count": 1,
"is_parallel": true,
"self": 0.00044816100023581384,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001576935999764828,
"count": 10,
"is_parallel": true,
"self": 0.001576935999764828
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 259.70890275201407,
"count": 18202,
"is_parallel": true,
"self": 10.50780163500474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.646136348998766,
"count": 18202,
"is_parallel": true,
"self": 5.646136348998766
},
"communicator.exchange": {
"total": 209.83599986500008,
"count": 18202,
"is_parallel": true,
"self": 209.83599986500008
},
"steps_from_proto": {
"total": 33.71896490301049,
"count": 18202,
"is_parallel": true,
"self": 7.7785194399621105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.940445463048377,
"count": 182020,
"is_parallel": true,
"self": 25.940445463048377
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001077060001080099,
"count": 1,
"self": 0.0001077060001080099,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 486.76710220312214,
"count": 438732,
"is_parallel": true,
"self": 11.101259312135767,
"children": {
"process_trajectory": {
"total": 280.161273750987,
"count": 438732,
"is_parallel": true,
"self": 279.47268612798723,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6885876229997621,
"count": 4,
"is_parallel": true,
"self": 0.6885876229997621
}
}
},
"_update_policy": {
"total": 195.50456913999938,
"count": 90,
"is_parallel": true,
"self": 69.29432042199608,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.2102487180033,
"count": 4584,
"is_parallel": true,
"self": 126.2102487180033
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11996216900001855,
"count": 1,
"self": 0.0009031499998854997,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11905901900013305,
"count": 1,
"self": 0.11905901900013305
}
}
}
}
}
}
}