ppo-Pyramids / run_logs /timers.json
faelwen's picture
First Push
26efa56 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.5332084894180298,
"min": 1.5332084894180298,
"max": 1.5332084894180298,
"count": 1
},
"Pyramids.Policy.Entropy.sum": {
"value": 46511.4140625,
"min": 46511.4140625,
"max": 46511.4140625,
"count": 1
},
"Pyramids.Step.mean": {
"value": 29951.0,
"min": 29951.0,
"max": 29951.0,
"count": 1
},
"Pyramids.Step.sum": {
"value": 29951.0,
"min": 29951.0,
"max": 29951.0,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.039321932941675186,
"min": -0.039321932941675186,
"max": -0.039321932941675186,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -9.319297790527344,
"min": -9.319297790527344,
"max": -9.319297790527344,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.17092017829418182,
"min": 0.17092017829418182,
"max": 0.17092017829418182,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 40.50808334350586,
"min": 40.50808334350586,
"max": 40.50808334350586,
"count": 1
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07060366959165978,
"min": 0.07060366959165978,
"max": 0.07060366959165978,
"count": 1
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.4942256871416185,
"min": 0.4942256871416185,
"max": 0.4942256871416185,
"count": 1
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.003736594842088565,
"min": 0.003736594842088565,
"max": 0.003736594842088565,
"count": 1
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.026156163894619954,
"min": 0.026156163894619954,
"max": 0.026156163894619954,
"count": 1
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00020301260375771423,
"min": 0.00020301260375771423,
"max": 0.00020301260375771423,
"count": 1
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0014210882263039997,
"min": 0.0014210882263039997,
"max": 0.0014210882263039997,
"count": 1
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.16767085714285712,
"min": 0.16767085714285712,
"max": 0.16767085714285712,
"count": 1
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.1736959999999999,
"min": 1.1736959999999999,
"max": 1.1736959999999999,
"count": 1
},
"Pyramids.Policy.Beta.mean": {
"value": 0.006770318628571428,
"min": 0.006770318628571428,
"max": 0.006770318628571428,
"count": 1
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0473922304,
"min": 0.0473922304,
"max": 0.0473922304,
"count": 1
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.33333688974380493,
"min": 0.33333688974380493,
"max": 0.33333688974380493,
"count": 1
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 2.3333582878112793,
"min": 2.3333582878112793,
"max": 2.3333582878112793,
"count": 1
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 992.8235294117648,
"min": 992.8235294117648,
"max": 992.8235294117648,
"count": 1
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 16878.0,
"min": 16878.0,
"max": 16878.0,
"count": 1
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.8761177010395947,
"min": -0.8761177010395947,
"max": -0.8761177010395947,
"count": 1
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -14.894000917673111,
"min": -14.894000917673111,
"max": -14.894000917673111,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.8761177010395947,
"min": -0.8761177010395947,
"max": -0.8761177010395947,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -14.894000917673111,
"min": -14.894000917673111,
"max": -14.894000917673111,
"count": 1
},
"Pyramids.Policy.RndReward.mean": {
"value": 6.413920536637306,
"min": 6.413920536637306,
"max": 6.413920536637306,
"count": 1
},
"Pyramids.Policy.RndReward.sum": {
"value": 109.0366491228342,
"min": 109.0366491228342,
"max": 109.0366491228342,
"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": "1741165640",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741165744"
},
"total": 103.88520427699996,
"count": 1,
"self": 0.476759914999775,
"children": {
"run_training.setup": {
"total": 0.028324853000185612,
"count": 1,
"self": 0.028324853000185612
},
"TrainerController.start_learning": {
"total": 103.380119509,
"count": 1,
"self": 0.07205535299817711,
"children": {
"TrainerController._reset_env": {
"total": 2.653581047999978,
"count": 1,
"self": 2.653581047999978
},
"TrainerController.advance": {
"total": 100.53455725200183,
"count": 3153,
"self": 0.07996089200514689,
"children": {
"env_step": {
"total": 65.50979874199606,
"count": 3153,
"self": 56.81276850800282,
"children": {
"SubprocessEnvManager._take_step": {
"total": 8.653775739991943,
"count": 3153,
"self": 0.2517579729967565,
"children": {
"TorchPolicy.evaluate": {
"total": 8.402017766995186,
"count": 3151,
"self": 8.402017766995186
}
}
},
"workers": {
"total": 0.0432544940013031,
"count": 3153,
"self": 0.0,
"children": {
"worker_root": {
"total": 103.053948153997,
"count": 3153,
"is_parallel": true,
"self": 52.187285205003036,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026350780001394014,
"count": 1,
"is_parallel": true,
"self": 0.0007600609999371954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001875017000202206,
"count": 8,
"is_parallel": true,
"self": 0.001875017000202206
}
}
},
"UnityEnvironment.step": {
"total": 0.05025113400006376,
"count": 1,
"is_parallel": true,
"self": 0.0006065620000299532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004579229998853407,
"count": 1,
"is_parallel": true,
"self": 0.0004579229998853407
},
"communicator.exchange": {
"total": 0.04720855699997628,
"count": 1,
"is_parallel": true,
"self": 0.04720855699997628
},
"steps_from_proto": {
"total": 0.0019780920001721825,
"count": 1,
"is_parallel": true,
"self": 0.0004605960004937515,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001517495999678431,
"count": 8,
"is_parallel": true,
"self": 0.001517495999678431
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 50.86666294899396,
"count": 3152,
"is_parallel": true,
"self": 1.6352032649892863,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.1539665770098964,
"count": 3152,
"is_parallel": true,
"self": 1.1539665770098964
},
"communicator.exchange": {
"total": 43.23337142200262,
"count": 3152,
"is_parallel": true,
"self": 43.23337142200262
},
"steps_from_proto": {
"total": 4.84412168499216,
"count": 3152,
"is_parallel": true,
"self": 0.9898245160043189,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.8542971689878414,
"count": 25216,
"is_parallel": true,
"self": 3.8542971689878414
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 34.94479761800062,
"count": 3153,
"self": 0.10233523199940464,
"children": {
"process_trajectory": {
"total": 6.163108425000701,
"count": 3153,
"self": 6.163108425000701
},
"_update_policy": {
"total": 28.679353961000515,
"count": 14,
"self": 15.834665257001234,
"children": {
"TorchPPOOptimizer.update": {
"total": 12.844688703999282,
"count": 1167,
"self": 12.844688703999282
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.639999578008428e-07,
"count": 1,
"self": 8.639999578008428e-07
},
"TrainerController._save_models": {
"total": 0.11992499200005113,
"count": 1,
"self": 0.0015125519998946402,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1184124400001565,
"count": 1,
"self": 0.1184124400001565
}
}
}
}
}
}
}