ppo-Huggy / run_logs /timers.json
Dawit-N's picture
Huggy
7e7158d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4048917293548584,
"min": 1.4048917293548584,
"max": 1.4255627393722534,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70260.0390625,
"min": 69087.515625,
"max": 75905.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.72994129158512,
"min": 83.59152542372881,
"max": 398.22222222222223,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49429.0,
"min": 48873.0,
"max": 50176.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999978.0,
"min": 49552.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999978.0,
"min": 49552.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.422793388366699,
"min": 0.046021681278944016,
"max": 2.494783878326416,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1238.04736328125,
"min": 5.752710342407227,
"max": 1451.155517578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6263514748991352,
"min": 1.7039547891616822,
"max": 3.961553008949503,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1853.065603673458,
"min": 212.99434864521027,
"max": 2234.3158970475197,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6263514748991352,
"min": 1.7039547891616822,
"max": 3.961553008949503,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1853.065603673458,
"min": 212.99434864521027,
"max": 2234.3158970475197,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01613932686159387,
"min": 0.013410382257037175,
"max": 0.02051676698902156,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04841798058478162,
"min": 0.02682076451407435,
"max": 0.06050411470544835,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04886867623362277,
"min": 0.02280328360696634,
"max": 0.05993019404510656,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1466060287008683,
"min": 0.04560656721393268,
"max": 0.1715606755266587,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.611048796350002e-06,
"min": 3.611048796350002e-06,
"max": 0.0002952933015689,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0833146389050006e-05,
"min": 1.0833146389050006e-05,
"max": 0.0008440419186526999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120364999999998,
"min": 0.10120364999999998,
"max": 0.19843110000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30361094999999994,
"min": 0.20756660000000005,
"max": 0.5813473000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.006213500000005e-05,
"min": 7.006213500000005e-05,
"max": 0.0049217118899999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021018640500000015,
"min": 0.00021018640500000015,
"max": 0.014069230269999997,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1739986628",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1739989020"
},
"total": 2391.4941596950002,
"count": 1,
"self": 0.4341633739995814,
"children": {
"run_training.setup": {
"total": 0.023322142999859352,
"count": 1,
"self": 0.023322142999859352
},
"TrainerController.start_learning": {
"total": 2391.036674178001,
"count": 1,
"self": 4.284525156164818,
"children": {
"TrainerController._reset_env": {
"total": 3.5286030900006153,
"count": 1,
"self": 3.5286030900006153
},
"TrainerController.advance": {
"total": 2383.1098628658356,
"count": 232497,
"self": 4.5051367296055105,
"children": {
"env_step": {
"total": 1889.018502305269,
"count": 232497,
"self": 1483.062576263329,
"children": {
"SubprocessEnvManager._take_step": {
"total": 403.4185602649195,
"count": 232497,
"self": 15.150951122870538,
"children": {
"TorchPolicy.evaluate": {
"total": 388.26760914204897,
"count": 223039,
"self": 388.26760914204897
}
}
},
"workers": {
"total": 2.537365777020568,
"count": 232497,
"self": 0.0,
"children": {
"worker_root": {
"total": 2383.8975689042536,
"count": 232497,
"is_parallel": true,
"self": 1172.6315141108807,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010404369995740126,
"count": 1,
"is_parallel": true,
"self": 0.0003536989988788264,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006867380006951862,
"count": 2,
"is_parallel": true,
"self": 0.0006867380006951862
}
}
},
"UnityEnvironment.step": {
"total": 0.07602906699958112,
"count": 1,
"is_parallel": true,
"self": 0.00030853000043862266,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017204400046466617,
"count": 1,
"is_parallel": true,
"self": 0.00017204400046466617
},
"communicator.exchange": {
"total": 0.07489577299929806,
"count": 1,
"is_parallel": true,
"self": 0.07489577299929806
},
"steps_from_proto": {
"total": 0.0006527199993797694,
"count": 1,
"is_parallel": true,
"self": 0.00016256399885605788,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004901560005237116,
"count": 2,
"is_parallel": true,
"self": 0.0004901560005237116
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1211.2660547933729,
"count": 232496,
"is_parallel": true,
"self": 36.81402724952022,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.7750372160217,
"count": 232496,
"is_parallel": true,
"self": 78.7750372160217
},
"communicator.exchange": {
"total": 1010.2663380580116,
"count": 232496,
"is_parallel": true,
"self": 1010.2663380580116
},
"steps_from_proto": {
"total": 85.41065226981937,
"count": 232496,
"is_parallel": true,
"self": 30.173125838600754,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.23752643121861,
"count": 464992,
"is_parallel": true,
"self": 55.23752643121861
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 489.586223830961,
"count": 232497,
"self": 6.24207456408476,
"children": {
"process_trajectory": {
"total": 159.22986244887306,
"count": 232497,
"self": 157.94713334387325,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2827291049998166,
"count": 10,
"self": 1.2827291049998166
}
}
},
"_update_policy": {
"total": 324.11428681800317,
"count": 97,
"self": 258.45907257996623,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.65521423803693,
"count": 2910,
"self": 65.65521423803693
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.190000148199033e-06,
"count": 1,
"self": 1.190000148199033e-06
},
"TrainerController._save_models": {
"total": 0.11368187599964585,
"count": 1,
"self": 0.0018645939999260008,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11181728199971985,
"count": 1,
"self": 0.11181728199971985
}
}
}
}
}
}
}