ppo-Huggy / run_logs /timers.json
Irisaka's picture
Huggy
6fe6f33 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046417474746704,
"min": 1.4046417474746704,
"max": 1.4246785640716553,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69998.9140625,
"min": 67829.8984375,
"max": 79405.28125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.51504424778761,
"min": 73.95652173913044,
"max": 392.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49446.0,
"min": 48775.0,
"max": 50228.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999924.0,
"min": 49860.0,
"max": 1999924.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999924.0,
"min": 49860.0,
"max": 1999924.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.460784435272217,
"min": 0.024427134543657303,
"max": 2.5371673107147217,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1390.3431396484375,
"min": 3.102246046066284,
"max": 1600.9619140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7945452818828347,
"min": 1.8298119132913004,
"max": 4.014282246005727,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2143.9180842638016,
"min": 232.38611298799515,
"max": 2485.546470940113,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7945452818828347,
"min": 1.8298119132913004,
"max": 4.014282246005727,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2143.9180842638016,
"min": 232.38611298799515,
"max": 2485.546470940113,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016069199143374943,
"min": 0.013831858399983805,
"max": 0.02012675990829141,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04820759743012483,
"min": 0.02766371679996761,
"max": 0.060380279724874225,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05446018833253119,
"min": 0.022572821968545514,
"max": 0.06187301663060983,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16338056499759357,
"min": 0.04514564393709103,
"max": 0.18147480661670368,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5354488215500035e-06,
"min": 3.5354488215500035e-06,
"max": 0.00029536965154345,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0606346464650011e-05,
"min": 1.0606346464650011e-05,
"max": 0.0008440203186598999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117845000000002,
"min": 0.10117845000000002,
"max": 0.19845655,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30353535000000004,
"min": 0.20749935000000003,
"max": 0.5813401000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.880465500000008e-05,
"min": 6.880465500000008e-05,
"max": 0.004922981845000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020641396500000023,
"min": 0.00020641396500000023,
"max": 0.01406887099,
"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": "1767012462",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/why/miniconda3/envs/drl-310/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767014736"
},
"total": 2274.2566063569393,
"count": 1,
"self": 0.4228272340260446,
"children": {
"run_training.setup": {
"total": 0.02640339802019298,
"count": 1,
"self": 0.02640339802019298
},
"TrainerController.start_learning": {
"total": 2273.807375724893,
"count": 1,
"self": 3.9408677688334137,
"children": {
"TrainerController._reset_env": {
"total": 3.2711224080994725,
"count": 1,
"self": 3.2711224080994725
},
"TrainerController.advance": {
"total": 2266.4945923897903,
"count": 232943,
"self": 3.5087286587804556,
"children": {
"env_step": {
"total": 1850.825122257229,
"count": 232943,
"self": 1512.7169424623717,
"children": {
"SubprocessEnvManager._take_step": {
"total": 335.6680565997958,
"count": 232943,
"self": 13.314747448079288,
"children": {
"TorchPolicy.evaluate": {
"total": 322.35330915171653,
"count": 223005,
"self": 322.35330915171653
}
}
},
"workers": {
"total": 2.44012319506146,
"count": 232943,
"self": 0.0,
"children": {
"worker_root": {
"total": 2266.480965931667,
"count": 232943,
"is_parallel": true,
"self": 988.8559964064043,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009898832067847252,
"count": 1,
"is_parallel": true,
"self": 0.0002819010987877846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007079821079969406,
"count": 2,
"is_parallel": true,
"self": 0.0007079821079969406
}
}
},
"UnityEnvironment.step": {
"total": 0.025619280990213156,
"count": 1,
"is_parallel": true,
"self": 0.00027982890605926514,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020514708012342453,
"count": 1,
"is_parallel": true,
"self": 0.00020514708012342453
},
"communicator.exchange": {
"total": 0.0244457870721817,
"count": 1,
"is_parallel": true,
"self": 0.0244457870721817
},
"steps_from_proto": {
"total": 0.0006885179318487644,
"count": 1,
"is_parallel": true,
"self": 0.00020455988124012947,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00048395805060863495,
"count": 2,
"is_parallel": true,
"self": 0.00048395805060863495
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1277.6249695252627,
"count": 232942,
"is_parallel": true,
"self": 33.82959466148168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 69.03490746882744,
"count": 232942,
"is_parallel": true,
"self": 69.03490746882744
},
"communicator.exchange": {
"total": 1093.9416291504167,
"count": 232942,
"is_parallel": true,
"self": 1093.9416291504167
},
"steps_from_proto": {
"total": 80.81883824453689,
"count": 232942,
"is_parallel": true,
"self": 27.548133827745914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.27070441679098,
"count": 465884,
"is_parallel": true,
"self": 53.27070441679098
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 412.16074147378094,
"count": 232943,
"self": 6.685293507995084,
"children": {
"process_trajectory": {
"total": 138.34748541144654,
"count": 232943,
"self": 136.8840783543419,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4634070571046323,
"count": 10,
"self": 1.4634070571046323
}
}
},
"_update_policy": {
"total": 267.1279625543393,
"count": 97,
"self": 216.0721203412395,
"children": {
"TorchPPOOptimizer.update": {
"total": 51.05584221309982,
"count": 2910,
"self": 51.05584221309982
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.849877536296844e-07,
"count": 1,
"self": 6.849877536296844e-07
},
"TrainerController._save_models": {
"total": 0.10079247318208218,
"count": 1,
"self": 0.0016730641946196556,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09911940898746252,
"count": 1,
"self": 0.09911940898746252
}
}
}
}
}
}
}