ppo-Huggy / run_logs /timers.json
ItchyB's picture
Huggy run2 4mil steps
901aab4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.331165075302124,
"min": 1.331165075302124,
"max": 1.424689531326294,
"count": 120
},
"Huggy.Policy.Entropy.sum": {
"value": 62375.73046875,
"min": 61831.640625,
"max": 159243.09375,
"count": 120
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 61.02900378310214,
"min": 54.73220338983051,
"max": 364.7883211678832,
"count": 120
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48396.0,
"min": 48396.0,
"max": 50092.0,
"count": 120
},
"Huggy.Step.mean": {
"value": 5999948.0,
"min": 49615.0,
"max": 5999948.0,
"count": 120
},
"Huggy.Step.sum": {
"value": 5999948.0,
"min": 49615.0,
"max": 5999948.0,
"count": 120
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.635014057159424,
"min": 0.06685349345207214,
"max": 2.694190740585327,
"count": 120
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 2092.201171875,
"min": 12.501603126525879,
"max": 2366.10400390625,
"count": 120
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.000148552566091,
"min": 1.7073887910116166,
"max": 4.1703113343735,
"count": 120
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 3176.1179507374763,
"min": 257.80516174435616,
"max": 3598.978681564331,
"count": 120
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.000148552566091,
"min": 1.7073887910116166,
"max": 4.1703113343735,
"count": 120
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 3176.1179507374763,
"min": 257.80516174435616,
"max": 3598.978681564331,
"count": 120
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01466162924544834,
"min": 0.01326285029402546,
"max": 0.02067570313811302,
"count": 120
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04398488773634502,
"min": 0.02652570058805092,
"max": 0.06202710941433907,
"count": 120
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06733244922426013,
"min": 0.01668465037105812,
"max": 0.07550323692460856,
"count": 120
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.20199734767278038,
"min": 0.03444100981578231,
"max": 0.20888847460349402,
"count": 120
},
"Huggy.Policy.LearningRate.mean": {
"value": 1.2643995785666626e-06,
"min": 1.2643995785666626e-06,
"max": 0.0002984526755157751,
"count": 120
},
"Huggy.Policy.LearningRate.sum": {
"value": 3.7931987356999877e-06,
"min": 3.7931987356999877e-06,
"max": 0.0008813472562175832,
"count": 120
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10042143333333331,
"min": 0.10042143333333331,
"max": 0.19948422500000002,
"count": 120
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30126429999999993,
"min": 0.2025559166666666,
"max": 0.5937824166666668,
"count": 120
},
"Huggy.Policy.Beta.mean": {
"value": 3.1029523333333256e-05,
"min": 3.1029523333333256e-05,
"max": 0.004974262827499999,
"count": 120
},
"Huggy.Policy.Beta.sum": {
"value": 9.308856999999977e-05,
"min": 9.308856999999977e-05,
"max": 0.014689742591666667,
"count": 120
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 120
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 120
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680811115",
"python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]",
"command_line_arguments": "/home/byron/mambaforge/envs/tensorflow/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=fHuggy-06-04-2023-15-58-33 --no-graphics --torch-device=cuda --results-dir reults --num-envs=16 --num-areas=16",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.0",
"numpy_version": "1.24.2",
"end_time_seconds": "1680813648"
},
"total": 2533.003975848027,
"count": 1,
"self": 0.334458330005873,
"children": {
"run_training.setup": {
"total": 0.06783929601078853,
"count": 1,
"self": 0.06783929601078853
},
"TrainerController.start_learning": {
"total": 2532.6016782220104,
"count": 1,
"self": 2.247419070394244,
"children": {
"TrainerController._reset_env": {
"total": 2.0328894879785366,
"count": 1,
"self": 2.0328894879785366
},
"TrainerController.advance": {
"total": 2528.2416661357274,
"count": 57508,
"self": 1.231277251150459,
"children": {
"env_step": {
"total": 1431.8029892065097,
"count": 57508,
"self": 335.17135497689014,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1093.5023788454127,
"count": 709843,
"self": 32.2855952460086,
"children": {
"TorchPolicy.evaluate": {
"total": 1061.2167835994042,
"count": 670583,
"self": 1061.2167835994042
}
}
},
"workers": {
"total": 3.129255384206772,
"count": 57508,
"self": 0.0,
"children": {
"worker_root": {
"total": 40480.93545381527,
"count": 709842,
"is_parallel": true,
"self": 37028.724816475646,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008291172969620675,
"count": 16,
"is_parallel": true,
"self": 0.0024210139526985586,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005870159016922116,
"count": 32,
"is_parallel": true,
"self": 0.005870159016922116
}
}
},
"UnityEnvironment.step": {
"total": 0.36801077309064567,
"count": 16,
"is_parallel": true,
"self": 0.00399885606020689,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.002076119009871036,
"count": 16,
"is_parallel": true,
"self": 0.002076119009871036
},
"communicator.exchange": {
"total": 0.3528424780233763,
"count": 16,
"is_parallel": true,
"self": 0.3528424780233763
},
"steps_from_proto": {
"total": 0.00909331999719143,
"count": 16,
"is_parallel": true,
"self": 0.002612037060316652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006481282936874777,
"count": 32,
"is_parallel": true,
"self": 0.006481282936874777
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3452.2106373396236,
"count": 709826,
"is_parallel": true,
"self": 81.59691327641485,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 140.57969102222705,
"count": 709826,
"is_parallel": true,
"self": 140.57969102222705
},
"communicator.exchange": {
"total": 3047.7782359896228,
"count": 709826,
"is_parallel": true,
"self": 3047.7782359896228
},
"steps_from_proto": {
"total": 182.25579705135897,
"count": 709826,
"is_parallel": true,
"self": 70.49089171068044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 111.76490534067852,
"count": 1419652,
"is_parallel": true,
"self": 111.76490534067852
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1095.2073996780673,
"count": 57508,
"self": 4.46831097221002,
"children": {
"process_trajectory": {
"total": 460.08666685182834,
"count": 57508,
"self": 457.494506941759,
"children": {
"RLTrainer._checkpoint": {
"total": 2.592159910069313,
"count": 30,
"self": 2.592159910069313
}
}
},
"_update_policy": {
"total": 630.652421854029,
"count": 291,
"self": 437.49230077612447,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.16012107790448,
"count": 8730,
"self": 193.16012107790448
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.09958078712225e-07,
"count": 1,
"self": 6.09958078712225e-07
},
"TrainerController._save_models": {
"total": 0.0797029179520905,
"count": 1,
"self": 0.00109528296161443,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07860763499047607,
"count": 1,
"self": 0.07860763499047607
}
}
}
}
}
}
}