Pittawat Taveekitworachai
First training of PyramidsTraining1
d6b3b65
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5899593234062195,
"min": 0.5229094624519348,
"max": 1.4632962942123413,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17661.021484375,
"min": 15720.75,
"max": 44390.5546875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989913.0,
"min": 29952.0,
"max": 989913.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989913.0,
"min": 29952.0,
"max": 989913.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.19840940833091736,
"min": -0.10729654133319855,
"max": 0.19840940833091736,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 49.4039421081543,
"min": -25.85846710205078,
"max": 49.4039421081543,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.05818955972790718,
"min": -0.05818955972790718,
"max": 0.4017461836338043,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -14.489200592041016,
"min": -14.489200592041016,
"max": 95.2138442993164,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06669780344554584,
"min": 0.06412217470351607,
"max": 0.07359657488994231,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9337692482376416,
"min": 0.49590501971840567,
"max": 1.070641634752974,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011476125740186091,
"min": 8.403715176590352e-05,
"max": 0.011476125740186091,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16066576036260527,
"min": 0.0010924829729567459,
"max": 0.16276145410423246,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.392140393128569e-06,
"min": 7.392140393128569e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010348996550379997,
"min": 0.00010348996550379997,
"max": 0.003254285615238199,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1024640142857143,
"min": 0.1024640142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4344962000000003,
"min": 1.3691136000000002,
"max": 2.3847618,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025615502714285707,
"min": 0.00025615502714285707,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003586170379999999,
"min": 0.003586170379999999,
"max": 0.10849770382000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012884699739515781,
"min": 0.012581122107803822,
"max": 0.4665043354034424,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1803857982158661,
"min": 0.17613570392131805,
"max": 3.2655303478240967,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 655.0,
"min": 655.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 25545.0,
"min": 15984.0,
"max": 33161.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.8320050984621048,
"min": -1.0000000521540642,
"max": 0.8320050984621048,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 32.44819884002209,
"min": -32.000001668930054,
"max": 35.67899890989065,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.8320050984621048,
"min": -1.0000000521540642,
"max": 0.8320050984621048,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 32.44819884002209,
"min": -32.000001668930054,
"max": 35.67899890989065,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08668025523925629,
"min": 0.08668025523925629,
"max": 9.926572669297457,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.3805299543309957,
"min": 3.3805299543309957,
"max": 158.8251627087593,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676101901",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676104036"
},
"total": 2134.807791994,
"count": 1,
"self": 0.43650476199991317,
"children": {
"run_training.setup": {
"total": 0.10516842000015458,
"count": 1,
"self": 0.10516842000015458
},
"TrainerController.start_learning": {
"total": 2134.266118812,
"count": 1,
"self": 1.2263632420877002,
"children": {
"TrainerController._reset_env": {
"total": 6.481882711000026,
"count": 1,
"self": 6.481882711000026
},
"TrainerController.advance": {
"total": 2126.472526378913,
"count": 63196,
"self": 1.2798699119671255,
"children": {
"env_step": {
"total": 1430.0687251910103,
"count": 63196,
"self": 1324.2121173520986,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.10086696093049,
"count": 63196,
"self": 4.333805177919885,
"children": {
"TorchPolicy.evaluate": {
"total": 100.7670617830106,
"count": 62570,
"self": 33.888961925045805,
"children": {
"TorchPolicy.sample_actions": {
"total": 66.8780998579648,
"count": 62570,
"self": 66.8780998579648
}
}
}
}
},
"workers": {
"total": 0.7557408779812249,
"count": 63196,
"self": 0.0,
"children": {
"worker_root": {
"total": 2129.9309441299974,
"count": 63196,
"is_parallel": true,
"self": 912.3509796209689,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017838929998106323,
"count": 1,
"is_parallel": true,
"self": 0.0006738570000379696,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011100359997726628,
"count": 8,
"is_parallel": true,
"self": 0.0011100359997726628
}
}
},
"UnityEnvironment.step": {
"total": 0.08752611799991428,
"count": 1,
"is_parallel": true,
"self": 0.000586546999784332,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004220640000767162,
"count": 1,
"is_parallel": true,
"self": 0.0004220640000767162
},
"communicator.exchange": {
"total": 0.07976159200006805,
"count": 1,
"is_parallel": true,
"self": 0.07976159200006805
},
"steps_from_proto": {
"total": 0.00675591499998518,
"count": 1,
"is_parallel": true,
"self": 0.00041974100031438866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006336173999670791,
"count": 8,
"is_parallel": true,
"self": 0.006336173999670791
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1217.5799645090285,
"count": 63195,
"is_parallel": true,
"self": 30.335581399098828,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.003944037950305,
"count": 63195,
"is_parallel": true,
"self": 22.003944037950305
},
"communicator.exchange": {
"total": 1044.384554684973,
"count": 63195,
"is_parallel": true,
"self": 1044.384554684973
},
"steps_from_proto": {
"total": 120.85588438700643,
"count": 63195,
"is_parallel": true,
"self": 21.72874007904079,
"children": {
"_process_rank_one_or_two_observation": {
"total": 99.12714430796564,
"count": 505560,
"is_parallel": true,
"self": 99.12714430796564
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 695.1239312759355,
"count": 63196,
"self": 2.288457264970475,
"children": {
"process_trajectory": {
"total": 151.3279650689626,
"count": 63196,
"self": 151.1026560429625,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2253090260001045,
"count": 2,
"self": 0.2253090260001045
}
}
},
"_update_policy": {
"total": 541.5075089420025,
"count": 440,
"self": 204.37792636300742,
"children": {
"TorchPPOOptimizer.update": {
"total": 337.12958257899504,
"count": 22860,
"self": 337.12958257899504
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.510000952810515e-07,
"count": 1,
"self": 8.510000952810515e-07
},
"TrainerController._save_models": {
"total": 0.08534562899967568,
"count": 1,
"self": 0.0013993399998071254,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08394628899986856,
"count": 1,
"self": 0.08394628899986856
}
}
}
}
}
}
}