ppo-Huggy2 / run_logs /timers.json
drilbo's picture
Huggy
a78e22c
raw
history blame contribute delete
No virus
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4191619157791138,
"min": 1.4179415702819824,
"max": 1.4191619157791138,
"count": 4
},
"Huggy.Policy.Entropy.sum": {
"value": 70340.7578125,
"min": 69248.4453125,
"max": 76497.3203125,
"count": 4
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 241.94174757281553,
"min": 241.94174757281553,
"max": 415.77685950413223,
"count": 4
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49840.0,
"min": 49702.0,
"max": 50309.0,
"count": 4
},
"Huggy.Step.mean": {
"value": 199982.0,
"min": 49680.0,
"max": 199982.0,
"count": 4
},
"Huggy.Step.sum": {
"value": 199982.0,
"min": 49680.0,
"max": 199982.0,
"count": 4
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7942177653312683,
"min": 0.03482276573777199,
"max": 0.7942177653312683,
"count": 4
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 163.60885620117188,
"min": 4.178731918334961,
"max": 163.60885620117188,
"count": 4
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.074964238023295,
"min": 1.772062095751365,
"max": 3.1007703384266625,
"count": 4
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 633.4426330327988,
"min": 212.6474514901638,
"max": 633.4426330327988,
"count": 4
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.074964238023295,
"min": 1.772062095751365,
"max": 3.1007703384266625,
"count": 4
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 633.4426330327988,
"min": 212.6474514901638,
"max": 633.4426330327988,
"count": 4
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017838396100948256,
"min": 0.014196641495315514,
"max": 0.018418121311212114,
"count": 4
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03567679220189651,
"min": 0.028393282990631027,
"max": 0.047739142139713905,
"count": 4
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.02598852797721823,
"min": 0.022510622752209504,
"max": 0.04715321566909551,
"count": 4
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.05197705595443646,
"min": 0.04502124550441901,
"max": 0.09430643133819103,
"count": 4
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.00010603133821874996,
"min": 0.00010603133821874996,
"max": 0.0007585425157175002,
"count": 4
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.00021206267643749993,
"min": 0.00021206267643749993,
"max": 0.0015170850314350005,
"count": 4
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.11178124999999998,
"min": 0.11178124999999998,
"max": 0.18428250000000004,
"count": 4
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.22356249999999997,
"min": 0.22356249999999997,
"max": 0.412661,
"count": 4
},
"Huggy.Policy.Beta.mean": {
"value": 0.0005978843750000002,
"min": 0.0005978843750000002,
"max": 0.004215696749999999,
"count": 4
},
"Huggy.Policy.Beta.sum": {
"value": 0.0011957687500000003,
"min": 0.0011957687500000003,
"max": 0.008431393499999999,
"count": 4
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1698546652",
"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/hug2.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698546896"
},
"total": 243.9998988159996,
"count": 1,
"self": 0.7840141649994621,
"children": {
"run_training.setup": {
"total": 0.04510211399974651,
"count": 1,
"self": 0.04510211399974651
},
"TrainerController.start_learning": {
"total": 243.17078253700038,
"count": 1,
"self": 0.4371802510077032,
"children": {
"TrainerController._reset_env": {
"total": 3.5379424259999723,
"count": 1,
"self": 3.5379424259999723
},
"TrainerController.advance": {
"total": 239.03246085999308,
"count": 22863,
"self": 0.4701989039349428,
"children": {
"env_step": {
"total": 192.37389533806618,
"count": 22863,
"self": 157.30643823807713,
"children": {
"SubprocessEnvManager._take_step": {
"total": 34.79615350499171,
"count": 22863,
"self": 1.7888166529974114,
"children": {
"TorchPolicy.evaluate": {
"total": 33.007336851994296,
"count": 22546,
"self": 33.007336851994296
}
}
},
"workers": {
"total": 0.2713035949973346,
"count": 22863,
"self": 0.0,
"children": {
"worker_root": {
"total": 242.06845651999538,
"count": 22863,
"is_parallel": true,
"self": 113.4074236321112,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007972010007506469,
"count": 1,
"is_parallel": true,
"self": 0.00021794700023747282,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005792540005131741,
"count": 2,
"is_parallel": true,
"self": 0.0005792540005131741
}
}
},
"UnityEnvironment.step": {
"total": 0.042558520999591565,
"count": 1,
"is_parallel": true,
"self": 0.0003132409992758767,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019790900023508584,
"count": 1,
"is_parallel": true,
"self": 0.00019790900023508584
},
"communicator.exchange": {
"total": 0.041266338000241376,
"count": 1,
"is_parallel": true,
"self": 0.041266338000241376
},
"steps_from_proto": {
"total": 0.0007810329998392262,
"count": 1,
"is_parallel": true,
"self": 0.00020996900002501206,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005710639998142142,
"count": 2,
"is_parallel": true,
"self": 0.0005710639998142142
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 128.66103288788418,
"count": 22862,
"is_parallel": true,
"self": 4.07709718886872,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.787568622012259,
"count": 22862,
"is_parallel": true,
"self": 8.787568622012259
},
"communicator.exchange": {
"total": 106.71250116203464,
"count": 22862,
"is_parallel": true,
"self": 106.71250116203464
},
"steps_from_proto": {
"total": 9.083865914968555,
"count": 22862,
"is_parallel": true,
"self": 3.1854861480142063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.898379766954349,
"count": 45724,
"is_parallel": true,
"self": 5.898379766954349
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 46.18836661799196,
"count": 22863,
"self": 0.6485221068696774,
"children": {
"process_trajectory": {
"total": 11.282518707122108,
"count": 22863,
"self": 11.08529934012222,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19721936699988873,
"count": 1,
"self": 0.19721936699988873
}
}
},
"_update_policy": {
"total": 34.257325804000175,
"count": 9,
"self": 28.502380665995588,
"children": {
"TorchPPOOptimizer.update": {
"total": 5.754945138004587,
"count": 270,
"self": 5.754945138004587
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.532999704068061e-06,
"count": 1,
"self": 1.532999704068061e-06
},
"TrainerController._save_models": {
"total": 0.1631974669999181,
"count": 1,
"self": 0.0049524969999765744,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15824496999994153,
"count": 1,
"self": 0.15824496999994153
}
}
}
}
}
}
}