ppo-huggy / run_logs /timers.json
nullaeon's picture
Huggy
47a959a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3997013568878174,
"min": 1.3997013568878174,
"max": 1.4273066520690918,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69267.0234375,
"min": 68411.703125,
"max": 75596.2578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.7540650406504,
"min": 82.43311036789298,
"max": 413.1885245901639,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49571.0,
"min": 48976.0,
"max": 50409.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999938.0,
"min": 49781.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999938.0,
"min": 49781.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4031598567962646,
"min": 0.049877215176820755,
"max": 2.418423652648926,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1179.9515380859375,
"min": 6.03514289855957,
"max": 1424.317626953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7457002787386084,
"min": 1.7042685887537712,
"max": 3.8849262542929335,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1839.1388368606567,
"min": 206.2164992392063,
"max": 2217.0239385962486,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7457002787386084,
"min": 1.7042685887537712,
"max": 3.8849262542929335,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1839.1388368606567,
"min": 206.2164992392063,
"max": 2217.0239385962486,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01677061381649562,
"min": 0.013361292472836794,
"max": 0.020872847504991417,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05031184144948686,
"min": 0.02672258494567359,
"max": 0.05593709484091959,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05204441679848565,
"min": 0.023130866978317496,
"max": 0.0627014022320509,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15613325039545695,
"min": 0.04626173395663499,
"max": 0.18186873259643715,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.287648904149995e-06,
"min": 3.287648904149995e-06,
"max": 0.0002953011015663,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.862946712449985e-06,
"min": 9.862946712449985e-06,
"max": 0.0008440795686401499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109585000000003,
"min": 0.10109585000000003,
"max": 0.1984337,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032875500000001,
"min": 0.20739174999999996,
"max": 0.5813598500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.468291499999992e-05,
"min": 6.468291499999992e-05,
"max": 0.004921841630000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019404874499999978,
"min": 0.00019404874499999978,
"max": 0.014069856515000001,
"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": "1743507359",
"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": "1743509828"
},
"total": 2469.2850061960003,
"count": 1,
"self": 0.4870883270000377,
"children": {
"run_training.setup": {
"total": 0.03421516299999894,
"count": 1,
"self": 0.03421516299999894
},
"TrainerController.start_learning": {
"total": 2468.763702706,
"count": 1,
"self": 4.540807395907905,
"children": {
"TrainerController._reset_env": {
"total": 3.2428612649999877,
"count": 1,
"self": 3.2428612649999877
},
"TrainerController.advance": {
"total": 2460.858787571092,
"count": 231916,
"self": 4.5831243290858765,
"children": {
"env_step": {
"total": 1964.2040097500314,
"count": 231916,
"self": 1543.4189414540128,
"children": {
"SubprocessEnvManager._take_step": {
"total": 418.05045865302486,
"count": 231916,
"self": 15.814771806033093,
"children": {
"TorchPolicy.evaluate": {
"total": 402.23568684699177,
"count": 222936,
"self": 402.23568684699177
}
}
},
"workers": {
"total": 2.7346096429936892,
"count": 231916,
"self": 0.0,
"children": {
"worker_root": {
"total": 2461.1959185429346,
"count": 231916,
"is_parallel": true,
"self": 1198.3465617069323,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011844349999705628,
"count": 1,
"is_parallel": true,
"self": 0.0002536719999852721,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009307629999852907,
"count": 2,
"is_parallel": true,
"self": 0.0009307629999852907
}
}
},
"UnityEnvironment.step": {
"total": 0.029169838000029813,
"count": 1,
"is_parallel": true,
"self": 0.0003152650000401991,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002075229999718431,
"count": 1,
"is_parallel": true,
"self": 0.0002075229999718431
},
"communicator.exchange": {
"total": 0.027943766000021242,
"count": 1,
"is_parallel": true,
"self": 0.027943766000021242
},
"steps_from_proto": {
"total": 0.000703283999996529,
"count": 1,
"is_parallel": true,
"self": 0.00018530599999166952,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005179780000048595,
"count": 2,
"is_parallel": true,
"self": 0.0005179780000048595
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1262.8493568360022,
"count": 231915,
"is_parallel": true,
"self": 37.62824026592489,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.86698540008445,
"count": 231915,
"is_parallel": true,
"self": 79.86698540008445
},
"communicator.exchange": {
"total": 1058.4329428769656,
"count": 231915,
"is_parallel": true,
"self": 1058.4329428769656
},
"steps_from_proto": {
"total": 86.92118829302723,
"count": 231915,
"is_parallel": true,
"self": 30.069388224004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.85180006902323,
"count": 463830,
"is_parallel": true,
"self": 56.85180006902323
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 492.07165349197464,
"count": 231916,
"self": 6.933293986991771,
"children": {
"process_trajectory": {
"total": 162.0918043599831,
"count": 231916,
"self": 160.71821638498312,
"children": {
"RLTrainer._checkpoint": {
"total": 1.373587974999964,
"count": 10,
"self": 1.373587974999964
}
}
},
"_update_policy": {
"total": 323.0465551449998,
"count": 97,
"self": 256.27509319399934,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.77146195100045,
"count": 2910,
"self": 66.77146195100045
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0600001587590668e-06,
"count": 1,
"self": 1.0600001587590668e-06
},
"TrainerController._save_models": {
"total": 0.12124541399998634,
"count": 1,
"self": 0.0019479009997667163,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11929751300021962,
"count": 1,
"self": 0.11929751300021962
}
}
}
}
}
}
}