ppo-Huggy / run_logs /timers.json
caiiofc's picture
Huggy
609fc2b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406630516052246,
"min": 1.406630516052246,
"max": 1.4299650192260742,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70844.9453125,
"min": 69031.1015625,
"max": 76959.546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.42526690391459,
"min": 80.55409836065574,
"max": 419.8666666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49695.0,
"min": 49028.0,
"max": 50384.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999531.0,
"min": 49948.0,
"max": 1999531.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999531.0,
"min": 49948.0,
"max": 1999531.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.42584490776062,
"min": 0.06266618520021439,
"max": 2.484623670578003,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1363.3248291015625,
"min": 7.457276344299316,
"max": 1468.7637939453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7890091900087337,
"min": 1.7741054821164668,
"max": 3.9327938818505834,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2129.4231647849083,
"min": 211.11855237185955,
"max": 2328.404710829258,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7890091900087337,
"min": 1.7741054821164668,
"max": 3.9327938818505834,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2129.4231647849083,
"min": 211.11855237185955,
"max": 2328.404710829258,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015510857134682332,
"min": 0.013365046620128851,
"max": 0.021183792505487672,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046532571404047,
"min": 0.026730093240257703,
"max": 0.06355137751646302,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05275366633302636,
"min": 0.02319464369987448,
"max": 0.05872912767032782,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15826099899907908,
"min": 0.04638928739974896,
"max": 0.17618738301098347,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6112987962666683e-06,
"min": 3.6112987962666683e-06,
"max": 0.00029534505155164996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0833896388800005e-05,
"min": 1.0833896388800005e-05,
"max": 0.0008440108686630498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120373333333332,
"min": 0.10120373333333332,
"max": 0.19844835,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30361119999999997,
"min": 0.20754340000000004,
"max": 0.5813369500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.006629333333342e-05,
"min": 7.006629333333342e-05,
"max": 0.004922572665,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021019888000000023,
"min": 0.00021019888000000023,
"max": 0.014068713804999999,
"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": "1716291426",
"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": "1716293833"
},
"total": 2406.901770901,
"count": 1,
"self": 0.7517536629998176,
"children": {
"run_training.setup": {
"total": 0.0760687429999507,
"count": 1,
"self": 0.0760687429999507
},
"TrainerController.start_learning": {
"total": 2406.073948495,
"count": 1,
"self": 4.298537044116529,
"children": {
"TrainerController._reset_env": {
"total": 3.448168836000036,
"count": 1,
"self": 3.448168836000036
},
"TrainerController.advance": {
"total": 2398.153493192883,
"count": 232292,
"self": 4.603851070843575,
"children": {
"env_step": {
"total": 1896.6476689980746,
"count": 232292,
"self": 1570.4959839389312,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.3756660500019,
"count": 232292,
"self": 16.475407664942395,
"children": {
"TorchPolicy.evaluate": {
"total": 306.9002583850595,
"count": 222946,
"self": 306.9002583850595
}
}
},
"workers": {
"total": 2.7760190091414643,
"count": 232292,
"self": 0.0,
"children": {
"worker_root": {
"total": 2398.7972544701106,
"count": 232292,
"is_parallel": true,
"self": 1131.998519930099,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010881869999366245,
"count": 1,
"is_parallel": true,
"self": 0.0003111959999841929,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007769909999524316,
"count": 2,
"is_parallel": true,
"self": 0.0007769909999524316
}
}
},
"UnityEnvironment.step": {
"total": 0.028824194999970132,
"count": 1,
"is_parallel": true,
"self": 0.0003877050000937743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020639699994262628,
"count": 1,
"is_parallel": true,
"self": 0.00020639699994262628
},
"communicator.exchange": {
"total": 0.02750483499994516,
"count": 1,
"is_parallel": true,
"self": 0.02750483499994516
},
"steps_from_proto": {
"total": 0.0007252579999885711,
"count": 1,
"is_parallel": true,
"self": 0.00019428100006280147,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005309769999257696,
"count": 2,
"is_parallel": true,
"self": 0.0005309769999257696
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1266.7987345400115,
"count": 232291,
"is_parallel": true,
"self": 39.02663482188382,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.20109887300407,
"count": 232291,
"is_parallel": true,
"self": 81.20109887300407
},
"communicator.exchange": {
"total": 1056.807314405068,
"count": 232291,
"is_parallel": true,
"self": 1056.807314405068
},
"steps_from_proto": {
"total": 89.7636864400555,
"count": 232291,
"is_parallel": true,
"self": 32.098340189969804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.66534625008569,
"count": 464582,
"is_parallel": true,
"self": 57.66534625008569
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 496.90197312396526,
"count": 232292,
"self": 6.468088568991448,
"children": {
"process_trajectory": {
"total": 158.46811606897234,
"count": 232292,
"self": 156.8891865359725,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5789295329998367,
"count": 10,
"self": 1.5789295329998367
}
}
},
"_update_policy": {
"total": 331.9657684860015,
"count": 97,
"self": 267.59606183000574,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.36970665599574,
"count": 2910,
"self": 64.36970665599574
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.154000074166106e-06,
"count": 1,
"self": 1.154000074166106e-06
},
"TrainerController._save_models": {
"total": 0.17374826800005394,
"count": 1,
"self": 0.0028442170000744227,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17090405099997952,
"count": 1,
"self": 0.17090405099997952
}
}
}
}
}
}
}