ppo-Pyramids / run_logs /timers.json
Sam017's picture
First Push
06b2206 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.24509786069393158,
"min": 0.24224235117435455,
"max": 1.4702414274215698,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 7317.6416015625,
"min": 7209.13232421875,
"max": 44601.2421875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989976.0,
"min": 29952.0,
"max": 989976.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989976.0,
"min": 29952.0,
"max": 989976.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7014859914779663,
"min": -0.10421880334615707,
"max": 0.7556648254394531,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 205.535400390625,
"min": -25.01251220703125,
"max": 225.1881103515625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.027868544682860374,
"min": -0.02354079857468605,
"max": 0.3842700719833374,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.165483474731445,
"min": -6.308934211730957,
"max": 91.07200622558594,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06785065768192346,
"min": 0.06495895333161267,
"max": 0.07287566864423042,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9499092075469283,
"min": 0.47741019553718983,
"max": 1.0472917339163057,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01448195831541116,
"min": 0.0017090319387832412,
"max": 0.018303744763278958,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20274741641575625,
"min": 0.015381287449049172,
"max": 0.27455617144918437,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.689868865314285e-06,
"min": 7.689868865314285e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010765816411439999,
"min": 0.00010765816411439999,
"max": 0.0036343645885451997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256325714285715,
"min": 0.10256325714285715,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358856,
"min": 1.3886848,
"max": 2.6622987,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002660693885714285,
"min": 0.0002660693885714285,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037249714399999996,
"min": 0.0037249714399999996,
"max": 0.12116433452,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00977993942797184,
"min": 0.00977993942797184,
"max": 0.38125142455101013,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13691915571689606,
"min": 0.13691915571689606,
"max": 2.668760061264038,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 275.88990825688074,
"min": 250.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30072.0,
"min": 15984.0,
"max": 33934.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6676907318609733,
"min": -1.0000000521540642,
"max": 1.72844543768601,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 180.1105990409851,
"min": -29.843001700937748,
"max": 204.798998311162,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6676907318609733,
"min": -1.0000000521540642,
"max": 1.72844543768601,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 180.1105990409851,
"min": -29.843001700937748,
"max": 204.798998311162,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.027587023900128703,
"min": 0.026452082312908746,
"max": 7.772831600159407,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.9793985812139,
"min": 2.9793985812139,
"max": 124.3653056025505,
"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": "1749857812",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749860151"
},
"total": 2338.750390451,
"count": 1,
"self": 0.5257573410003715,
"children": {
"run_training.setup": {
"total": 0.020755196999971304,
"count": 1,
"self": 0.020755196999971304
},
"TrainerController.start_learning": {
"total": 2338.203877913,
"count": 1,
"self": 1.3311282670106266,
"children": {
"TrainerController._reset_env": {
"total": 2.1416810779999196,
"count": 1,
"self": 2.1416810779999196
},
"TrainerController.advance": {
"total": 2334.651103788989,
"count": 64507,
"self": 1.4317888840578235,
"children": {
"env_step": {
"total": 1681.068441397964,
"count": 64507,
"self": 1531.4082527569828,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.82841569699508,
"count": 64507,
"self": 4.673673309039259,
"children": {
"TorchPolicy.evaluate": {
"total": 144.15474238795582,
"count": 62564,
"self": 144.15474238795582
}
}
},
"workers": {
"total": 0.8317729439861523,
"count": 64507,
"self": 0.0,
"children": {
"worker_root": {
"total": 2332.759826235009,
"count": 64507,
"is_parallel": true,
"self": 915.2562107260412,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018457040000612324,
"count": 1,
"is_parallel": true,
"self": 0.0006447090001984179,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012009949998628144,
"count": 8,
"is_parallel": true,
"self": 0.0012009949998628144
}
}
},
"UnityEnvironment.step": {
"total": 0.04729677099999208,
"count": 1,
"is_parallel": true,
"self": 0.0005530400001134694,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004422990000421123,
"count": 1,
"is_parallel": true,
"self": 0.0004422990000421123
},
"communicator.exchange": {
"total": 0.04466378600000098,
"count": 1,
"is_parallel": true,
"self": 0.04466378600000098
},
"steps_from_proto": {
"total": 0.001637645999835513,
"count": 1,
"is_parallel": true,
"self": 0.0003648390002126689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012728069996228442,
"count": 8,
"is_parallel": true,
"self": 0.0012728069996228442
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1417.5036155089676,
"count": 64506,
"is_parallel": true,
"self": 31.819744646979643,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.731770713976857,
"count": 64506,
"is_parallel": true,
"self": 22.731770713976857
},
"communicator.exchange": {
"total": 1265.950959367004,
"count": 64506,
"is_parallel": true,
"self": 1265.950959367004
},
"steps_from_proto": {
"total": 97.00114078100705,
"count": 64506,
"is_parallel": true,
"self": 19.556711532959753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.4444292480473,
"count": 516048,
"is_parallel": true,
"self": 77.4444292480473
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 652.1508735069672,
"count": 64507,
"self": 2.7189048149978134,
"children": {
"process_trajectory": {
"total": 129.4289018719644,
"count": 64507,
"self": 129.1838687529646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24503311899979963,
"count": 2,
"self": 0.24503311899979963
}
}
},
"_update_policy": {
"total": 520.003066820005,
"count": 456,
"self": 288.5116953329741,
"children": {
"TorchPPOOptimizer.update": {
"total": 231.49137148703085,
"count": 22800,
"self": 231.49137148703085
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.860003279347438e-07,
"count": 1,
"self": 7.860003279347438e-07
},
"TrainerController._save_models": {
"total": 0.07996399300009216,
"count": 1,
"self": 0.0011585479996938375,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07880544500039832,
"count": 1,
"self": 0.07880544500039832
}
}
}
}
}
}
}