ppo-Pyramids / run_logs /timers.json
power-is-me's picture
First Push
1b86038 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.340847134590149,
"min": 1.340847134590149,
"max": 1.340847134590149,
"count": 1
},
"Pyramids.Policy.Entropy.sum": {
"value": 40675.9375,
"min": 40675.9375,
"max": 40675.9375,
"count": 1
},
"Pyramids.Step.mean": {
"value": 29905.0,
"min": 29905.0,
"max": 29905.0,
"count": 1
},
"Pyramids.Step.sum": {
"value": 29905.0,
"min": 29905.0,
"max": 29905.0,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.0067672645673155785,
"min": -0.0067672645673155785,
"max": -0.0067672645673155785,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -1.6038416624069214,
"min": -1.6038416624069214,
"max": -1.6038416624069214,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.3892833888530731,
"min": 0.3892833888530731,
"max": 0.3892833888530731,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 92.26016235351562,
"min": 92.26016235351562,
"max": 92.26016235351562,
"count": 1
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0720027475259046,
"min": 0.0720027475259046,
"max": 0.0720027475259046,
"count": 1
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.5040192326813322,
"min": 0.5040192326813322,
"max": 0.5040192326813322,
"count": 1
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011484924391466079,
"min": 0.011484924391466079,
"max": 0.011484924391466079,
"count": 1
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.08039447074026256,
"min": 0.08039447074026256,
"max": 0.08039447074026256,
"count": 1
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00029838354339596195,
"min": 0.00029838354339596195,
"max": 0.00029838354339596195,
"count": 1
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0020886848037717336,
"min": 0.0020886848037717336,
"max": 0.0020886848037717336,
"count": 1
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.19946118095238097,
"min": 0.19946118095238097,
"max": 0.19946118095238097,
"count": 1
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.3962282666666668,
"min": 1.3962282666666668,
"max": 1.3962282666666668,
"count": 1
},
"Pyramids.Policy.Beta.mean": {
"value": 0.009946171977142856,
"min": 0.009946171977142856,
"max": 0.009946171977142856,
"count": 1
},
"Pyramids.Policy.Beta.sum": {
"value": 0.06962320384,
"min": 0.06962320384,
"max": 0.06962320384,
"count": 1
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.6465741395950317,
"min": 0.6465741395950317,
"max": 0.6465741395950317,
"count": 1
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 4.526019096374512,
"min": 4.526019096374512,
"max": 4.526019096374512,
"count": 1
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 990.1176470588235,
"min": 990.1176470588235,
"max": 990.1176470588235,
"count": 1
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 16832.0,
"min": 16832.0,
"max": 16832.0,
"count": 1
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.8734118184622597,
"min": -0.8734118184622597,
"max": -0.8734118184622597,
"count": 1
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -14.848000913858414,
"min": -14.848000913858414,
"max": -14.848000913858414,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.8734118184622597,
"min": -0.8734118184622597,
"max": -0.8734118184622597,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -14.848000913858414,
"min": -14.848000913858414,
"max": -14.848000913858414,
"count": 1
},
"Pyramids.Policy.RndReward.mean": {
"value": 13.7276410705903,
"min": 13.7276410705903,
"max": 13.7276410705903,
"count": 1
},
"Pyramids.Policy.RndReward.sum": {
"value": 233.3698982000351,
"min": 233.3698982000351,
"max": 233.3698982000351,
"count": 1
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1731945795",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731945890"
},
"total": 94.97946768200018,
"count": 1,
"self": 0.40210428800014597,
"children": {
"run_training.setup": {
"total": 0.07757717200001935,
"count": 1,
"self": 0.07757717200001935
},
"TrainerController.start_learning": {
"total": 94.49978622200001,
"count": 1,
"self": 0.07062670600362253,
"children": {
"TrainerController._reset_env": {
"total": 2.3880601369999113,
"count": 1,
"self": 2.3880601369999113
},
"TrainerController.advance": {
"total": 91.8616038649966,
"count": 2329,
"self": 0.07329196599653187,
"children": {
"env_step": {
"total": 59.04787735100149,
"count": 2329,
"self": 53.9192521020002,
"children": {
"SubprocessEnvManager._take_step": {
"total": 5.088017505000607,
"count": 2329,
"self": 0.20627495500662008,
"children": {
"TorchPolicy.evaluate": {
"total": 4.881742549993987,
"count": 2328,
"self": 4.881742549993987
}
}
},
"workers": {
"total": 0.04060774400068112,
"count": 2328,
"self": 0.0,
"children": {
"worker_root": {
"total": 94.12536740900646,
"count": 2328,
"is_parallel": true,
"self": 45.581988025995315,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022671679998893524,
"count": 1,
"is_parallel": true,
"self": 0.0007025129996236501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015646550002657023,
"count": 8,
"is_parallel": true,
"self": 0.0015646550002657023
}
}
},
"UnityEnvironment.step": {
"total": 0.05520073700017747,
"count": 1,
"is_parallel": true,
"self": 0.0007546030003595661,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005702339999515971,
"count": 1,
"is_parallel": true,
"self": 0.0005702339999515971
},
"communicator.exchange": {
"total": 0.05193237299999964,
"count": 1,
"is_parallel": true,
"self": 0.05193237299999964
},
"steps_from_proto": {
"total": 0.0019435269998666627,
"count": 1,
"is_parallel": true,
"self": 0.00041044600038731005,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015330809994793526,
"count": 8,
"is_parallel": true,
"self": 0.0015330809994793526
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 48.54337938301114,
"count": 2327,
"is_parallel": true,
"self": 1.6270099910109366,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.024647518002439,
"count": 2327,
"is_parallel": true,
"self": 1.024647518002439
},
"communicator.exchange": {
"total": 41.49708094499897,
"count": 2327,
"is_parallel": true,
"self": 41.49708094499897
},
"steps_from_proto": {
"total": 4.394640928998797,
"count": 2327,
"is_parallel": true,
"self": 0.9051447529827783,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.4894961760160186,
"count": 18616,
"is_parallel": true,
"self": 3.4894961760160186
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 32.740434547998575,
"count": 2328,
"self": 0.08975342299527256,
"children": {
"process_trajectory": {
"total": 5.307159117003266,
"count": 2328,
"self": 5.307159117003266
},
"_update_policy": {
"total": 27.343522008000036,
"count": 9,
"self": 11.444946535001918,
"children": {
"TorchPPOOptimizer.update": {
"total": 15.898575472998118,
"count": 795,
"self": 15.898575472998118
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6649998997309012e-06,
"count": 1,
"self": 1.6649998997309012e-06
},
"TrainerController._save_models": {
"total": 0.17949384899998222,
"count": 1,
"self": 0.002365221999980349,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17712862700000187,
"count": 1,
"self": 0.17712862700000187
}
}
}
}
}
}
}