ppo-Pyramids / run_logs /timers.json
AmroAsw's picture
First push
b40626e verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.13582871854305267,
"min": 0.12172577530145645,
"max": 1.5214966535568237,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4072.6884765625,
"min": 3606.978271484375,
"max": 46156.12109375,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999986.0,
"min": 29952.0,
"max": 2999986.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999986.0,
"min": 29952.0,
"max": 2999986.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8127821087837219,
"min": -0.1003299131989479,
"max": 0.8769814372062683,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 249.52410888671875,
"min": -24.27983856201172,
"max": 266.60235595703125,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.025562865659594536,
"min": -0.030753938481211662,
"max": 0.2001783847808838,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.847799777984619,
"min": -8.98015022277832,
"max": 48.24299240112305,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06935793843824045,
"min": 0.062371556149585,
"max": 0.07368105282616202,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9710111381353663,
"min": 0.511834949434296,
"max": 1.0800797568009848,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016704138723728366,
"min": 0.00041459381511710624,
"max": 0.017235334800347824,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2338579421321971,
"min": 0.004560531966288169,
"max": 0.25853002200521735,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5094494968833352e-06,
"min": 1.5094494968833352e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.1132292956366692e-05,
"min": 2.1132292956366692e-05,
"max": 0.0038846341051219997,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10050311666666666,
"min": 0.10050311666666666,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4070436333333332,
"min": 1.3962282666666668,
"max": 2.7823485666666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.026135500000008e-05,
"min": 6.026135500000008e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008436589700000011,
"min": 0.0008436589700000011,
"max": 0.1294983122,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007638160604983568,
"min": 0.007523938547819853,
"max": 0.382885605096817,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10693424940109253,
"min": 0.10533513873815536,
"max": 2.680199146270752,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 207.01342281879195,
"min": 200.81884057971016,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30845.0,
"min": 15984.0,
"max": 32984.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7658608043314636,
"min": -1.0000000521540642,
"max": 1.7991970724215474,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 261.34739904105663,
"min": -30.553001701831818,
"max": 261.34739904105663,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7658608043314636,
"min": -1.0000000521540642,
"max": 1.7991970724215474,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 261.34739904105663,
"min": -30.553001701831818,
"max": 261.34739904105663,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.016264674431924406,
"min": 0.016264674431924406,
"max": 7.6446228651329875,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.407171815924812,
"min": 2.3180334985954687,
"max": 122.3139658421278,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1756600956",
"python_version": "3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]",
"command_line_arguments": "/root/DeepRL_HuggingFace/Unit3/.venv/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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1756607922"
},
"total": 6965.818022993,
"count": 1,
"self": 0.8896225950047665,
"children": {
"run_training.setup": {
"total": 0.026464598999154987,
"count": 1,
"self": 0.026464598999154987
},
"TrainerController.start_learning": {
"total": 6964.901935798996,
"count": 1,
"self": 4.206516890251805,
"children": {
"TrainerController._reset_env": {
"total": 4.674266572998022,
"count": 1,
"self": 4.674266572998022
},
"TrainerController.advance": {
"total": 6955.909802535742,
"count": 195414,
"self": 4.1061645995905565,
"children": {
"env_step": {
"total": 4512.785445527581,
"count": 195414,
"self": 3754.883364683279,
"children": {
"SubprocessEnvManager._take_step": {
"total": 755.2205336405023,
"count": 195414,
"self": 14.057658510428155,
"children": {
"TorchPolicy.evaluate": {
"total": 741.1628751300741,
"count": 187561,
"self": 741.1628751300741
}
}
},
"workers": {
"total": 2.6815472037997097,
"count": 195414,
"self": 0.0,
"children": {
"worker_root": {
"total": 6955.091959799687,
"count": 195414,
"is_parallel": true,
"self": 3483.2844398210364,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027248999977018684,
"count": 1,
"is_parallel": true,
"self": 0.001575199992657872,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011497000050439965,
"count": 8,
"is_parallel": true,
"self": 0.0011497000050439965
}
}
},
"UnityEnvironment.step": {
"total": 0.032844697998370975,
"count": 1,
"is_parallel": true,
"self": 0.00024029999622143805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018710000222199596,
"count": 1,
"is_parallel": true,
"self": 0.00018710000222199596
},
"communicator.exchange": {
"total": 0.03175509799984866,
"count": 1,
"is_parallel": true,
"self": 0.03175509799984866
},
"steps_from_proto": {
"total": 0.000662200000078883,
"count": 1,
"is_parallel": true,
"self": 0.0001644000003580004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004977999997208826,
"count": 8,
"is_parallel": true,
"self": 0.0004977999997208826
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3471.807519978651,
"count": 195413,
"is_parallel": true,
"self": 47.742896208197635,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 37.087616161908954,
"count": 195413,
"is_parallel": true,
"self": 37.087616161908954
},
"communicator.exchange": {
"total": 3249.86985856713,
"count": 195413,
"is_parallel": true,
"self": 3249.86985856713
},
"steps_from_proto": {
"total": 137.10714904141423,
"count": 195413,
"is_parallel": true,
"self": 34.30403579376798,
"children": {
"_process_rank_one_or_two_observation": {
"total": 102.80311324764625,
"count": 1563304,
"is_parallel": true,
"self": 102.80311324764625
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2439.01819240857,
"count": 195414,
"self": 7.8875250062774285,
"children": {
"process_trajectory": {
"total": 456.13164830819005,
"count": 195414,
"self": 455.5128537071905,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6187946009995358,
"count": 6,
"self": 0.6187946009995358
}
}
},
"_update_policy": {
"total": 1974.9990190941026,
"count": 1394,
"self": 868.0929121078989,
"children": {
"TorchPPOOptimizer.update": {
"total": 1106.9061069862037,
"count": 68361,
"self": 1106.9061069862037
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.00005330145359e-07,
"count": 1,
"self": 7.00005330145359e-07
},
"TrainerController._save_models": {
"total": 0.11134909999964293,
"count": 1,
"self": 0.003261700003349688,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10808739999629324,
"count": 1,
"self": 0.10808739999629324
}
}
}
}
}
}
}