rl-ppo-Huggy / run_logs /timers.json
Ketan3101's picture
Huggy
461e753 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3970814943313599,
"min": 1.3970814943313599,
"max": 1.427712082862854,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69317.59375,
"min": 68414.0859375,
"max": 78379.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 71.19219653179191,
"min": 65.26887417218543,
"max": 384.05384615384617,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49265.0,
"min": 49007.0,
"max": 49943.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49402.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49402.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.538844585418701,
"min": -0.008325384929776192,
"max": 2.538844585418701,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1756.88037109375,
"min": -1.073974609375,
"max": 1865.454345703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9673799874121056,
"min": 1.5290371590806533,
"max": 4.056154556747745,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2745.426951289177,
"min": 197.24579352140427,
"max": 2953.07103317976,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9673799874121056,
"min": 1.5290371590806533,
"max": 4.056154556747745,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2745.426951289177,
"min": 197.24579352140427,
"max": 2953.07103317976,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017425996259973747,
"min": 0.013713093521073461,
"max": 0.02102832728560315,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052277988779921236,
"min": 0.027426187042146923,
"max": 0.05595439877967388,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05497921312020885,
"min": 0.023633883179475866,
"max": 0.06207685992121696,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16493763936062655,
"min": 0.04726776635895173,
"max": 0.17756173809369405,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.1719986093666615e-06,
"min": 4.1719986093666615e-06,
"max": 0.00029537685154105,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2515995828099984e-05,
"min": 1.2515995828099984e-05,
"max": 0.0008443315685561499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10139063333333335,
"min": 0.10139063333333335,
"max": 0.19845895000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30417190000000005,
"min": 0.20790550000000005,
"max": 0.5814438500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.939260333333327e-05,
"min": 7.939260333333327e-05,
"max": 0.004923101605000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002381778099999998,
"min": 0.0002381778099999998,
"max": 0.014074048114999998,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1710137113",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710139755"
},
"total": 2642.480057381,
"count": 1,
"self": 0.9003087159999268,
"children": {
"run_training.setup": {
"total": 0.07044982299998992,
"count": 1,
"self": 0.07044982299998992
},
"TrainerController.start_learning": {
"total": 2641.509298842,
"count": 1,
"self": 5.024234725070073,
"children": {
"TrainerController._reset_env": {
"total": 3.025263922000022,
"count": 1,
"self": 3.025263922000022
},
"TrainerController.advance": {
"total": 2633.3312314079303,
"count": 233958,
"self": 4.979941800928827,
"children": {
"env_step": {
"total": 2101.6864264770484,
"count": 233958,
"self": 1747.6892490998398,
"children": {
"SubprocessEnvManager._take_step": {
"total": 350.6818096141154,
"count": 233958,
"self": 19.143340201169167,
"children": {
"TorchPolicy.evaluate": {
"total": 331.53846941294626,
"count": 222934,
"self": 331.53846941294626
}
}
},
"workers": {
"total": 3.3153677630931497,
"count": 233958,
"self": 0.0,
"children": {
"worker_root": {
"total": 2633.6734107859916,
"count": 233958,
"is_parallel": true,
"self": 1221.9863702469092,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010057770000457822,
"count": 1,
"is_parallel": true,
"self": 0.0002712440000323113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007345330000134709,
"count": 2,
"is_parallel": true,
"self": 0.0007345330000134709
}
}
},
"UnityEnvironment.step": {
"total": 0.033169338999982756,
"count": 1,
"is_parallel": true,
"self": 0.0004491329998472793,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022990200000094774,
"count": 1,
"is_parallel": true,
"self": 0.00022990200000094774
},
"communicator.exchange": {
"total": 0.031589570000051026,
"count": 1,
"is_parallel": true,
"self": 0.031589570000051026
},
"steps_from_proto": {
"total": 0.0009007340000835029,
"count": 1,
"is_parallel": true,
"self": 0.00025331400013328675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006474199999502162,
"count": 2,
"is_parallel": true,
"self": 0.0006474199999502162
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1411.6870405390823,
"count": 233957,
"is_parallel": true,
"self": 43.397046368986594,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.73983921700199,
"count": 233957,
"is_parallel": true,
"self": 90.73983921700199
},
"communicator.exchange": {
"total": 1175.054843891965,
"count": 233957,
"is_parallel": true,
"self": 1175.054843891965
},
"steps_from_proto": {
"total": 102.49531106112863,
"count": 233957,
"is_parallel": true,
"self": 36.70142293619119,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.79388812493744,
"count": 467914,
"is_parallel": true,
"self": 65.79388812493744
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 526.6648631299532,
"count": 233958,
"self": 7.253402465007639,
"children": {
"process_trajectory": {
"total": 177.26913194294582,
"count": 233958,
"self": 175.92812191994608,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3410100229997397,
"count": 10,
"self": 1.3410100229997397
}
}
},
"_update_policy": {
"total": 342.1423287219998,
"count": 97,
"self": 275.40006213199536,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.74226659000442,
"count": 2910,
"self": 66.74226659000442
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.93999947240809e-07,
"count": 1,
"self": 9.93999947240809e-07
},
"TrainerController._save_models": {
"total": 0.12856779300000198,
"count": 1,
"self": 0.003173232999870379,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1253945600001316,
"count": 1,
"self": 0.1253945600001316
}
}
}
}
}
}
}