ppo-Huggy / run_logs /timers.json
AndVilches's picture
Huggy
ff8e4fe verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4053081274032593,
"min": 1.4053081274032593,
"max": 1.4240280389785767,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69672.3671875,
"min": 66989.46875,
"max": 77428.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.87076923076923,
"min": 73.36255572065379,
"max": 406.479674796748,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49316.0,
"min": 48928.0,
"max": 50189.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999943.0,
"min": 49370.0,
"max": 1999943.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999943.0,
"min": 49370.0,
"max": 1999943.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.461918592453003,
"min": -0.11544552445411682,
"max": 2.5188100337982178,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1602.708984375,
"min": -14.084354400634766,
"max": 1630.7291259765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8310589750974042,
"min": 1.7284232822598005,
"max": 4.071788160350379,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2494.01939278841,
"min": 210.86764043569565,
"max": 2525.1154153347015,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8310589750974042,
"min": 1.7284232822598005,
"max": 4.071788160350379,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2494.01939278841,
"min": 210.86764043569565,
"max": 2525.1154153347015,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016934423842192497,
"min": 0.013901027041720228,
"max": 0.021834494609599155,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05080327152657749,
"min": 0.027802054083440456,
"max": 0.05756811314301254,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06396366519232591,
"min": 0.02420894910270969,
"max": 0.06497197838293182,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19189099557697772,
"min": 0.04841789820541938,
"max": 0.19491593514879546,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7685487438500004e-06,
"min": 3.7685487438500004e-06,
"max": 0.000295368076543975,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1305646231550002e-05,
"min": 1.1305646231550002e-05,
"max": 0.00084409516863495,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125614999999999,
"min": 0.10125614999999999,
"max": 0.19845602500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30376844999999997,
"min": 0.20763715000000002,
"max": 0.58136505,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.268188500000003e-05,
"min": 7.268188500000003e-05,
"max": 0.0049229556474999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021804565500000008,
"min": 0.00021804565500000008,
"max": 0.014070115995,
"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": "1740049622",
"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": "1740052068"
},
"total": 2445.697021333,
"count": 1,
"self": 0.44018184000015026,
"children": {
"run_training.setup": {
"total": 0.02673188599999321,
"count": 1,
"self": 0.02673188599999321
},
"TrainerController.start_learning": {
"total": 2445.230107607,
"count": 1,
"self": 4.475659717043527,
"children": {
"TrainerController._reset_env": {
"total": 3.600105744000075,
"count": 1,
"self": 3.600105744000075
},
"TrainerController.advance": {
"total": 2437.0289978699566,
"count": 232648,
"self": 4.81405484581137,
"children": {
"env_step": {
"total": 1932.9124449951735,
"count": 232648,
"self": 1508.484709576177,
"children": {
"SubprocessEnvManager._take_step": {
"total": 421.82791859303825,
"count": 232648,
"self": 15.497387885131502,
"children": {
"TorchPolicy.evaluate": {
"total": 406.33053070790675,
"count": 222902,
"self": 406.33053070790675
}
}
},
"workers": {
"total": 2.5998168259581007,
"count": 232648,
"self": 0.0,
"children": {
"worker_root": {
"total": 2437.7178267750255,
"count": 232648,
"is_parallel": true,
"self": 1207.093317504089,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013342519999923752,
"count": 1,
"is_parallel": true,
"self": 0.0005143139999290725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008199380000633028,
"count": 2,
"is_parallel": true,
"self": 0.0008199380000633028
}
}
},
"UnityEnvironment.step": {
"total": 0.029992533000040567,
"count": 1,
"is_parallel": true,
"self": 0.0003339489999234502,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019251399999120622,
"count": 1,
"is_parallel": true,
"self": 0.00019251399999120622
},
"communicator.exchange": {
"total": 0.028722628000082295,
"count": 1,
"is_parallel": true,
"self": 0.028722628000082295
},
"steps_from_proto": {
"total": 0.0007434420000436148,
"count": 1,
"is_parallel": true,
"self": 0.0002130390000729676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005304029999706472,
"count": 2,
"is_parallel": true,
"self": 0.0005304029999706472
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1230.6245092709364,
"count": 232647,
"is_parallel": true,
"self": 37.387365186100396,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.1532827699217,
"count": 232647,
"is_parallel": true,
"self": 80.1532827699217
},
"communicator.exchange": {
"total": 1026.2883266250583,
"count": 232647,
"is_parallel": true,
"self": 1026.2883266250583
},
"steps_from_proto": {
"total": 86.79553468985614,
"count": 232647,
"is_parallel": true,
"self": 30.381703625728505,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.413831064127635,
"count": 465294,
"is_parallel": true,
"self": 56.413831064127635
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 499.3024980289715,
"count": 232648,
"self": 6.633071941898947,
"children": {
"process_trajectory": {
"total": 165.68939131907234,
"count": 232648,
"self": 164.27034466407292,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4190466549994198,
"count": 10,
"self": 1.4190466549994198
}
}
},
"_update_policy": {
"total": 326.9800347680002,
"count": 97,
"self": 259.8758371460033,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.10419762199695,
"count": 2910,
"self": 67.10419762199695
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.589998626324814e-07,
"count": 1,
"self": 9.589998626324814e-07
},
"TrainerController._save_models": {
"total": 0.12534331699998802,
"count": 1,
"self": 0.002179493999847182,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12316382300014084,
"count": 1,
"self": 0.12316382300014084
}
}
}
}
}
}
}