ppo-Huggy / run_logs /timers.json
SaraPiscitelli's picture
Trained a ppo agent on Huggy environment
fd2e9f2
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3998006582260132,
"min": 1.3998006582260132,
"max": 1.4272023439407349,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69194.9453125,
"min": 67751.78125,
"max": 75544.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.47504621072089,
"min": 75.71932515337423,
"max": 417.28333333333336,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49488.0,
"min": 49241.0,
"max": 50074.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999968.0,
"min": 49444.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999968.0,
"min": 49444.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4567933082580566,
"min": 0.07157561182975769,
"max": 2.5135066509246826,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1329.125244140625,
"min": 8.517498016357422,
"max": 1627.0843505859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6846552008621796,
"min": 1.8091764585310672,
"max": 3.993220277620931,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1993.398463666439,
"min": 215.291998565197,
"max": 2545.5754188895226,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6846552008621796,
"min": 1.8091764585310672,
"max": 3.993220277620931,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1993.398463666439,
"min": 215.291998565197,
"max": 2545.5754188895226,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016287364680384702,
"min": 0.013577443333876242,
"max": 0.021632525106381056,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0488620940411541,
"min": 0.027154886667752485,
"max": 0.06489757531914317,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05415089416007201,
"min": 0.021869140304625036,
"max": 0.06380855329334736,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16245268248021602,
"min": 0.04373828060925007,
"max": 0.18688746728003025,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2604989131999965e-06,
"min": 3.2604989131999965e-06,
"max": 0.0002953650765449749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.78149673959999e-06,
"min": 9.78149673959999e-06,
"max": 0.00084419506860165,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108679999999998,
"min": 0.10108679999999998,
"max": 0.19845502500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30326039999999993,
"min": 0.20735050000000002,
"max": 0.58139835,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.423131999999996e-05,
"min": 6.423131999999996e-05,
"max": 0.004922905747499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019269395999999987,
"min": 0.00019269395999999987,
"max": 0.014071777665,
"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": "1701125885",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701128492"
},
"total": 2606.331602055,
"count": 1,
"self": 0.4386316960003569,
"children": {
"run_training.setup": {
"total": 0.0578761230000282,
"count": 1,
"self": 0.0578761230000282
},
"TrainerController.start_learning": {
"total": 2605.835094236,
"count": 1,
"self": 4.7164029870650666,
"children": {
"TrainerController._reset_env": {
"total": 3.4524357049999708,
"count": 1,
"self": 3.4524357049999708
},
"TrainerController.advance": {
"total": 2597.5551381679347,
"count": 232619,
"self": 5.248476828915045,
"children": {
"env_step": {
"total": 2064.1013671130204,
"count": 232619,
"self": 1706.2973381051193,
"children": {
"SubprocessEnvManager._take_step": {
"total": 354.51953024594786,
"count": 232619,
"self": 19.585398118034277,
"children": {
"TorchPolicy.evaluate": {
"total": 334.9341321279136,
"count": 222983,
"self": 334.9341321279136
}
}
},
"workers": {
"total": 3.284498761953273,
"count": 232619,
"self": 0.0,
"children": {
"worker_root": {
"total": 2597.839221838983,
"count": 232619,
"is_parallel": true,
"self": 1217.5345810150093,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009352030000400191,
"count": 1,
"is_parallel": true,
"self": 0.0002698069999951258,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006653960000448933,
"count": 2,
"is_parallel": true,
"self": 0.0006653960000448933
}
}
},
"UnityEnvironment.step": {
"total": 0.03299833299990951,
"count": 1,
"is_parallel": true,
"self": 0.00032553699998061347,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024198099993100186,
"count": 1,
"is_parallel": true,
"self": 0.00024198099993100186
},
"communicator.exchange": {
"total": 0.03167649299996356,
"count": 1,
"is_parallel": true,
"self": 0.03167649299996356
},
"steps_from_proto": {
"total": 0.0007543220000343354,
"count": 1,
"is_parallel": true,
"self": 0.00022837900007743883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005259429999568965,
"count": 2,
"is_parallel": true,
"self": 0.0005259429999568965
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1380.3046408239738,
"count": 232618,
"is_parallel": true,
"self": 42.508222180951634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.56040768593789,
"count": 232618,
"is_parallel": true,
"self": 92.56040768593789
},
"communicator.exchange": {
"total": 1148.6785350799987,
"count": 232618,
"is_parallel": true,
"self": 1148.6785350799987
},
"steps_from_proto": {
"total": 96.5574758770855,
"count": 232618,
"is_parallel": true,
"self": 36.48635192488757,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.07112395219792,
"count": 465236,
"is_parallel": true,
"self": 60.07112395219792
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 528.2052942259994,
"count": 232619,
"self": 7.551763565067631,
"children": {
"process_trajectory": {
"total": 169.90018258292946,
"count": 232619,
"self": 168.4146443069301,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4855382759993745,
"count": 10,
"self": 1.4855382759993745
}
}
},
"_update_policy": {
"total": 350.7533480780023,
"count": 97,
"self": 285.68095214200696,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.07239593599536,
"count": 2910,
"self": 65.07239593599536
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0290000318491366e-06,
"count": 1,
"self": 1.0290000318491366e-06
},
"TrainerController._save_models": {
"total": 0.1111163470000065,
"count": 1,
"self": 0.0018486520002625184,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10926769499974398,
"count": 1,
"self": 0.10926769499974398
}
}
}
}
}
}
}