|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7200339436531067, |
|
"min": 0.4707546830177307, |
|
"max": 1.449265718460083, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 21566.45703125, |
|
"min": 14341.0703125, |
|
"max": 43964.92578125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479996.0, |
|
"min": 29952.0, |
|
"max": 479996.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479996.0, |
|
"min": 29952.0, |
|
"max": 479996.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.04102286696434021, |
|
"min": -0.10457050055265427, |
|
"max": 0.02314971201121807, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -9.927534103393555, |
|
"min": -25.20149040222168, |
|
"max": 5.486481666564941, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.024904629215598106, |
|
"min": 0.024904629215598106, |
|
"max": 0.3518091142177582, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 6.026920318603516, |
|
"min": 6.026920318603516, |
|
"max": 83.3787612915039, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06915890673282739, |
|
"min": 0.06584193825888661, |
|
"max": 0.07366409289827842, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9682246942595834, |
|
"min": 0.5055383530596937, |
|
"max": 1.006904313910305, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0023833787373642285, |
|
"min": 0.00025102184266071213, |
|
"max": 0.009312412937973953, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.0333673023230992, |
|
"min": 0.003263283954589258, |
|
"max": 0.06518689056581767, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.1460721417885714e-05, |
|
"min": 2.1460721417885714e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0003004500998504, |
|
"min": 0.0003004500998504, |
|
"max": 0.0030636373787876004, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10715354285714286, |
|
"min": 0.10715354285714286, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5001496, |
|
"min": 1.3773696000000002, |
|
"max": 2.250616, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007246389314285714, |
|
"min": 0.0007246389314285714, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.01014494504, |
|
"min": 0.01014494504, |
|
"max": 0.10213911876000001, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.024579446762800217, |
|
"min": 0.024579446762800217, |
|
"max": 0.31865277886390686, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.34411224722862244, |
|
"min": 0.34411224722862244, |
|
"max": 2.230569362640381, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 960.125, |
|
"min": 926.4411764705883, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30724.0, |
|
"min": 15984.0, |
|
"max": 33425.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.6367677882794411, |
|
"min": -1.0000000521540642, |
|
"max": -0.5151941664516926, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -19.739801436662674, |
|
"min": -31.99600164592266, |
|
"max": -15.496201001107693, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.6367677882794411, |
|
"min": -1.0000000521540642, |
|
"max": -0.5151941664516926, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -19.739801436662674, |
|
"min": -31.99600164592266, |
|
"max": -15.496201001107693, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.24409166408041794, |
|
"min": 0.24409166408041794, |
|
"max": 5.75393873360008, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 7.566841586492956, |
|
"min": 7.319175027310848, |
|
"max": 92.06301973760128, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1667748738", |
|
"python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1667749739" |
|
}, |
|
"total": 1000.450517303, |
|
"count": 1, |
|
"self": 0.4412835980001546, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0427472969999485, |
|
"count": 1, |
|
"self": 0.0427472969999485 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 999.9664864079999, |
|
"count": 1, |
|
"self": 0.6992696720113827, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 11.065005683000038, |
|
"count": 1, |
|
"self": 11.065005683000038 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 988.1062711789885, |
|
"count": 31516, |
|
"self": 0.763293201004899, |
|
"children": { |
|
"env_step": { |
|
"total": 628.9146043609869, |
|
"count": 31516, |
|
"self": 573.4650578369829, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 55.08251274000514, |
|
"count": 31516, |
|
"self": 2.379871411020133, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 52.70264132898501, |
|
"count": 31305, |
|
"self": 18.161379056976614, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 34.541262272008396, |
|
"count": 31305, |
|
"self": 34.541262272008396 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.367033783998977, |
|
"count": 31516, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 997.5217788719876, |
|
"count": 31516, |
|
"is_parallel": true, |
|
"self": 476.6564096239988, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.004731350999975348, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0032994979999898533, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014318529999854945, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014318529999854945 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04741398199996638, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005841119999558941, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005243229999791765, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005243229999791765 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.044591325999988385, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.044591325999988385 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017142210000429259, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042930300003263255, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012849180000102933, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012849180000102933 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 520.8653692479888, |
|
"count": 31515, |
|
"is_parallel": true, |
|
"self": 14.613723985986326, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.382065680993264, |
|
"count": 31515, |
|
"is_parallel": true, |
|
"self": 12.382065680993264 |
|
}, |
|
"communicator.exchange": { |
|
"total": 440.36727685300735, |
|
"count": 31515, |
|
"is_parallel": true, |
|
"self": 440.36727685300735 |
|
}, |
|
"steps_from_proto": { |
|
"total": 53.502302728001894, |
|
"count": 31515, |
|
"is_parallel": true, |
|
"self": 12.465775055032566, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 41.03652767296933, |
|
"count": 252120, |
|
"is_parallel": true, |
|
"self": 41.03652767296933 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 358.42837361699674, |
|
"count": 31516, |
|
"self": 1.1777485950126447, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 83.5377486139842, |
|
"count": 31516, |
|
"self": 83.4265798589841, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11116875500010792, |
|
"count": 1, |
|
"self": 0.11116875500010792 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 273.7128764079999, |
|
"count": 213, |
|
"self": 108.63322691801494, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 165.07964948998494, |
|
"count": 11484, |
|
"self": 165.07964948998494 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0899998414970469e-06, |
|
"count": 1, |
|
"self": 1.0899998414970469e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09593878400005451, |
|
"count": 1, |
|
"self": 0.0016598489999068988, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09427893500014761, |
|
"count": 1, |
|
"self": 0.09427893500014761 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |