ppo-Huggy / run_logs /timers.json
sohail756's picture
Huggy
2ebb0b3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4063669443130493,
"min": 1.4063669443130493,
"max": 1.4287091493606567,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69800.8046875,
"min": 69415.15625,
"max": 76556.6328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.30992366412214,
"min": 74.15765765765765,
"max": 411.27868852459017,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49328.0,
"min": 49140.0,
"max": 50296.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49648.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49648.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4835879802703857,
"min": 0.10250949114561081,
"max": 2.4927241802215576,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1626.7501220703125,
"min": 12.403648376464844,
"max": 1650.1834716796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.852487560446936,
"min": 1.723531886812084,
"max": 3.9733423195540793,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2523.379352092743,
"min": 208.54735830426216,
"max": 2548.442698597908,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.852487560446936,
"min": 1.723531886812084,
"max": 3.9733423195540793,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2523.379352092743,
"min": 208.54735830426216,
"max": 2548.442698597908,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019995475251784633,
"min": 0.013872651513277864,
"max": 0.019995475251784633,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0599864257553539,
"min": 0.02774530302655573,
"max": 0.0599864257553539,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059414326440956865,
"min": 0.023030355790009102,
"max": 0.06226594398419063,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1782429793228706,
"min": 0.046060711580018204,
"max": 0.18679783195257188,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.744098752000003e-06,
"min": 3.744098752000003e-06,
"max": 0.0002952786765737749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.123229625600001e-05,
"min": 1.123229625600001e-05,
"max": 0.0008439195186934999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101248,
"min": 0.101248,
"max": 0.19842622499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.303744,
"min": 0.20763160000000003,
"max": 0.5813065000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.227520000000006e-05,
"min": 7.227520000000006e-05,
"max": 0.0049214686275,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002168256000000002,
"min": 0.0002168256000000002,
"max": 0.01406719435,
"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": "1733582065",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733584541"
},
"total": 2476.049575009,
"count": 1,
"self": 0.42609504399979414,
"children": {
"run_training.setup": {
"total": 0.06127386700001125,
"count": 1,
"self": 0.06127386700001125
},
"TrainerController.start_learning": {
"total": 2475.562206098,
"count": 1,
"self": 4.669325024016416,
"children": {
"TrainerController._reset_env": {
"total": 5.1133038450000186,
"count": 1,
"self": 5.1133038450000186
},
"TrainerController.advance": {
"total": 2465.671543479983,
"count": 233039,
"self": 4.556585614134292,
"children": {
"env_step": {
"total": 1934.9951611619397,
"count": 233039,
"self": 1523.224482449955,
"children": {
"SubprocessEnvManager._take_step": {
"total": 408.92915632398297,
"count": 233039,
"self": 15.782770130051858,
"children": {
"TorchPolicy.evaluate": {
"total": 393.1463861939311,
"count": 222894,
"self": 393.1463861939311
}
}
},
"workers": {
"total": 2.8415223880016356,
"count": 233039,
"self": 0.0,
"children": {
"worker_root": {
"total": 2468.2856833810074,
"count": 233039,
"is_parallel": true,
"self": 1231.9757531459254,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008438360000013745,
"count": 1,
"is_parallel": true,
"self": 0.00022712999998475425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006167060000166202,
"count": 2,
"is_parallel": true,
"self": 0.0006167060000166202
}
}
},
"UnityEnvironment.step": {
"total": 0.046277594000002864,
"count": 1,
"is_parallel": true,
"self": 0.00039899600000126156,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002805980000175623,
"count": 1,
"is_parallel": true,
"self": 0.0002805980000175623
},
"communicator.exchange": {
"total": 0.04484257899997601,
"count": 1,
"is_parallel": true,
"self": 0.04484257899997601
},
"steps_from_proto": {
"total": 0.0007554210000080275,
"count": 1,
"is_parallel": true,
"self": 0.00021123000004763526,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005441909999603922,
"count": 2,
"is_parallel": true,
"self": 0.0005441909999603922
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1236.309930235082,
"count": 233038,
"is_parallel": true,
"self": 38.520783777100405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.25910040896656,
"count": 233038,
"is_parallel": true,
"self": 83.25910040896656
},
"communicator.exchange": {
"total": 1025.0698632160047,
"count": 233038,
"is_parallel": true,
"self": 1025.0698632160047
},
"steps_from_proto": {
"total": 89.46018283301026,
"count": 233038,
"is_parallel": true,
"self": 31.729638956925044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.73054387608522,
"count": 466076,
"is_parallel": true,
"self": 57.73054387608522
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 526.119796703909,
"count": 233039,
"self": 6.328446890928831,
"children": {
"process_trajectory": {
"total": 174.72226777098115,
"count": 233039,
"self": 173.34103129598088,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3812364750002644,
"count": 10,
"self": 1.3812364750002644
}
}
},
"_update_policy": {
"total": 345.06908204199897,
"count": 97,
"self": 277.35146942400655,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.71761261799242,
"count": 2910,
"self": 67.71761261799242
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0420003491162788e-06,
"count": 1,
"self": 1.0420003491162788e-06
},
"TrainerController._save_models": {
"total": 0.10803270699989298,
"count": 1,
"self": 0.0020672040000135894,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10596550299987939,
"count": 1,
"self": 0.10596550299987939
}
}
}
}
}
}
}