ppo-Huggy / run_logs /timers.json
abragin's picture
Initial commit
efe0613 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4021137952804565,
"min": 1.4021137952804565,
"max": 1.424363136291504,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69860.3203125,
"min": 68579.140625,
"max": 78366.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.0541958041958,
"min": 81.69028006589785,
"max": 407.1219512195122,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49223.0,
"min": 49172.0,
"max": 50076.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999968.0,
"min": 49575.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999968.0,
"min": 49575.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.49231219291687,
"min": 0.036642663180828094,
"max": 2.49231219291687,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1425.6025390625,
"min": 4.470405101776123,
"max": 1466.26318359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8983336210876076,
"min": 1.8142348370346866,
"max": 3.999221385466425,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2229.8468312621117,
"min": 221.33665011823177,
"max": 2302.644550859928,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8983336210876076,
"min": 1.8142348370346866,
"max": 3.999221385466425,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2229.8468312621117,
"min": 221.33665011823177,
"max": 2302.644550859928,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015332559728752434,
"min": 0.013742294547167452,
"max": 0.02045030511362711,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0459976791862573,
"min": 0.027484589094334905,
"max": 0.05447134217004835,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05523177360494932,
"min": 0.02192513324941198,
"max": 0.06103190742433072,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16569532081484795,
"min": 0.04385026649882396,
"max": 0.1762098031739394,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3221488926499977e-06,
"min": 3.3221488926499977e-06,
"max": 0.00029527582657472507,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.966446677949993e-06,
"min": 9.966446677949993e-06,
"max": 0.0008435728688090499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110735000000003,
"min": 0.10110735000000003,
"max": 0.198425275,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30332205000000007,
"min": 0.20736259999999995,
"max": 0.58119095,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.525676499999999e-05,
"min": 6.525676499999999e-05,
"max": 0.0049214212225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000195770295,
"min": 0.000195770295,
"max": 0.014061428405000003,
"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": "1705156512",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1705159103"
},
"total": 2591.409865278,
"count": 1,
"self": 0.44150488099967333,
"children": {
"run_training.setup": {
"total": 0.05112700799998038,
"count": 1,
"self": 0.05112700799998038
},
"TrainerController.start_learning": {
"total": 2590.917233389,
"count": 1,
"self": 4.7373465600080635,
"children": {
"TrainerController._reset_env": {
"total": 3.2333172649999824,
"count": 1,
"self": 3.2333172649999824
},
"TrainerController.advance": {
"total": 2582.8247061689917,
"count": 232222,
"self": 5.094860178066483,
"children": {
"env_step": {
"total": 2045.261548454001,
"count": 232222,
"self": 1699.4192357022132,
"children": {
"SubprocessEnvManager._take_step": {
"total": 342.7239720119017,
"count": 232222,
"self": 17.468614000906882,
"children": {
"TorchPolicy.evaluate": {
"total": 325.2553580109948,
"count": 222966,
"self": 325.2553580109948
}
}
},
"workers": {
"total": 3.1183407398861505,
"count": 232222,
"self": 0.0,
"children": {
"worker_root": {
"total": 2583.117974517045,
"count": 232222,
"is_parallel": true,
"self": 1204.4037507819921,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007183569999824613,
"count": 1,
"is_parallel": true,
"self": 0.00023383799998555332,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00048451899999690795,
"count": 2,
"is_parallel": true,
"self": 0.00048451899999690795
}
}
},
"UnityEnvironment.step": {
"total": 0.03250251199995091,
"count": 1,
"is_parallel": true,
"self": 0.00037343199994666065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001971130000129051,
"count": 1,
"is_parallel": true,
"self": 0.0001971130000129051
},
"communicator.exchange": {
"total": 0.03113556799996786,
"count": 1,
"is_parallel": true,
"self": 0.03113556799996786
},
"steps_from_proto": {
"total": 0.0007963990000234844,
"count": 1,
"is_parallel": true,
"self": 0.00020782300003929777,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005885759999841866,
"count": 2,
"is_parallel": true,
"self": 0.0005885759999841866
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1378.7142237350527,
"count": 232221,
"is_parallel": true,
"self": 43.30550823525732,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.84171736400953,
"count": 232221,
"is_parallel": true,
"self": 90.84171736400953
},
"communicator.exchange": {
"total": 1147.5304034768483,
"count": 232221,
"is_parallel": true,
"self": 1147.5304034768483
},
"steps_from_proto": {
"total": 97.03659465893753,
"count": 232221,
"is_parallel": true,
"self": 36.36049757485188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.676097084085654,
"count": 464442,
"is_parallel": true,
"self": 60.676097084085654
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 532.4682975369241,
"count": 232222,
"self": 7.215581859845884,
"children": {
"process_trajectory": {
"total": 163.84593326207943,
"count": 232222,
"self": 162.5217310570792,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3242022050002333,
"count": 10,
"self": 1.3242022050002333
}
}
},
"_update_policy": {
"total": 361.4067824149988,
"count": 97,
"self": 294.9846203459921,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.42216206900673,
"count": 2910,
"self": 66.42216206900673
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1850002010760363e-06,
"count": 1,
"self": 1.1850002010760363e-06
},
"TrainerController._save_models": {
"total": 0.12186221000001751,
"count": 1,
"self": 0.0024722630000724166,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1193899469999451,
"count": 1,
"self": 0.1193899469999451
}
}
}
}
}
}
}