ppo-pyramid / run_logs /timers.json
dhmeltzer's picture
first push
eaca3d6
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.19597655534744263,
"min": 0.18826612830162048,
"max": 1.356343150138855,
"count": 66
},
"Pyramids.Policy.Entropy.sum": {
"value": 5785.22802734375,
"min": 5629.91015625,
"max": 41146.02734375,
"count": 66
},
"Pyramids.Step.mean": {
"value": 1979988.0,
"min": 29952.0,
"max": 1979988.0,
"count": 66
},
"Pyramids.Step.sum": {
"value": 1979988.0,
"min": 29952.0,
"max": 1979988.0,
"count": 66
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6133843660354614,
"min": -0.08936651051044464,
"max": 0.6436856389045715,
"count": 66
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 173.5877685546875,
"min": -21.447961807250977,
"max": 185.3814697265625,
"count": 66
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.024124663323163986,
"min": -0.024641381576657295,
"max": 1.7748193740844727,
"count": 66
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.827279567718506,
"min": -6.554607391357422,
"max": 429.50628662109375,
"count": 66
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.02626937720924616,
"min": 0.02626937720924616,
"max": 0.03862767101963982,
"count": 66
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.3677712809294462,
"min": 0.27039369713747874,
"max": 0.4955255749324958,
"count": 66
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013958490012945343,
"min": 0.0012675715979206697,
"max": 0.10142276285067327,
"count": 66
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1954188601812348,
"min": 0.017746002370889375,
"max": 0.7099593399547128,
"count": 66
},
"Pyramids.Policy.LearningRate.mean": {
"value": 5.2528089633821435e-06,
"min": 5.2528089633821435e-06,
"max": 0.0002975753150939428,
"count": 66
},
"Pyramids.Policy.LearningRate.sum": {
"value": 7.353932548735e-05,
"min": 7.353932548735e-05,
"max": 0.003978955873681399,
"count": 66
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10175090357142857,
"min": 0.10175090357142857,
"max": 0.1991917714285714,
"count": 66
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.42451265,
"min": 1.3943423999999998,
"max": 2.7263186000000004,
"count": 66
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00018491526678571433,
"min": 0.00018491526678571433,
"max": 0.009919257965714285,
"count": 66
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0025888137350000007,
"min": 0.0025888137350000007,
"max": 0.13263922814,
"count": 66
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.022599434480071068,
"min": 0.022599434480071068,
"max": 2.6360156536102295,
"count": 66
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.31639209389686584,
"min": 0.31639209389686584,
"max": 18.452110290527344,
"count": 66
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 320.19354838709677,
"min": 275.89719626168227,
"max": 999.0,
"count": 66
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29778.0,
"min": 15984.0,
"max": 33156.0,
"count": 66
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.633665203643234,
"min": -1.0000000521540642,
"max": 1.7054093236399588,
"count": 66
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 150.29719873517752,
"min": -29.710801661014557,
"max": 182.4787976294756,
"count": 66
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.633665203643234,
"min": -1.0000000521540642,
"max": 1.7054093236399588,
"count": 66
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 150.29719873517752,
"min": -29.710801661014557,
"max": 182.4787976294756,
"count": 66
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0734409268732871,
"min": 0.06912152861379887,
"max": 40.698184706270695,
"count": 66
},
"Pyramids.Policy.RndReward.sum": {
"value": 6.756565272342414,
"min": 6.756565272342414,
"max": 651.1709553003311,
"count": 66
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 66
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 66
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675222862",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "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": "1675226494"
},
"total": 3631.7672543119997,
"count": 1,
"self": 0.4429739659999541,
"children": {
"run_training.setup": {
"total": 0.09933592100014721,
"count": 1,
"self": 0.09933592100014721
},
"TrainerController.start_learning": {
"total": 3631.2249444249996,
"count": 1,
"self": 2.4069282758900954,
"children": {
"TrainerController._reset_env": {
"total": 5.899183773999994,
"count": 1,
"self": 5.899183773999994
},
"TrainerController.advance": {
"total": 3622.70665457011,
"count": 128200,
"self": 2.5237377189937433,
"children": {
"env_step": {
"total": 2617.306834976167,
"count": 128200,
"self": 2415.8746097681815,
"children": {
"SubprocessEnvManager._take_step": {
"total": 199.96061796905042,
"count": 128200,
"self": 8.051847826997346,
"children": {
"TorchPolicy.evaluate": {
"total": 191.90877014205307,
"count": 125073,
"self": 64.30314346398245,
"children": {
"TorchPolicy.sample_actions": {
"total": 127.60562667807062,
"count": 125073,
"self": 127.60562667807062
}
}
}
}
},
"workers": {
"total": 1.4716072389351211,
"count": 128200,
"self": 0.0,
"children": {
"worker_root": {
"total": 3625.093728456983,
"count": 128200,
"is_parallel": true,
"self": 1394.1844787409032,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016480139997838705,
"count": 1,
"is_parallel": true,
"self": 0.0006127519995970943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010352620001867763,
"count": 8,
"is_parallel": true,
"self": 0.0010352620001867763
}
}
},
"UnityEnvironment.step": {
"total": 0.04413425199982157,
"count": 1,
"is_parallel": true,
"self": 0.0004694259996540495,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004106490000594931,
"count": 1,
"is_parallel": true,
"self": 0.0004106490000594931
},
"communicator.exchange": {
"total": 0.04174069500004407,
"count": 1,
"is_parallel": true,
"self": 0.04174069500004407
},
"steps_from_proto": {
"total": 0.0015134820000639593,
"count": 1,
"is_parallel": true,
"self": 0.00038831799929539557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011251640007685637,
"count": 8,
"is_parallel": true,
"self": 0.0011251640007685637
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2230.90924971608,
"count": 128199,
"is_parallel": true,
"self": 54.035412490249655,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 42.137213799160236,
"count": 128199,
"is_parallel": true,
"self": 42.137213799160236
},
"communicator.exchange": {
"total": 1959.980963901899,
"count": 128199,
"is_parallel": true,
"self": 1959.980963901899
},
"steps_from_proto": {
"total": 174.7556595247711,
"count": 128199,
"is_parallel": true,
"self": 41.12610857398067,
"children": {
"_process_rank_one_or_two_observation": {
"total": 133.62955095079042,
"count": 1025592,
"is_parallel": true,
"self": 133.62955095079042
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1002.8760818749493,
"count": 128200,
"self": 4.576908499141155,
"children": {
"process_trajectory": {
"total": 286.2514396587958,
"count": 128200,
"self": 285.5787658547956,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6726738040001692,
"count": 4,
"self": 0.6726738040001692
}
}
},
"_update_policy": {
"total": 712.0477337170123,
"count": 926,
"self": 364.7691677380071,
"children": {
"TorchPPOOptimizer.update": {
"total": 347.2785659790052,
"count": 11304,
"self": 347.2785659790052
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.91999809734989e-07,
"count": 1,
"self": 7.91999809734989e-07
},
"TrainerController._save_models": {
"total": 0.21217701299974578,
"count": 1,
"self": 0.004022598999654292,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2081544140000915,
"count": 1,
"self": 0.2081544140000915
}
}
}
}
}
}
}