ppo-Huggy / run_logs /timers.json
virdel's picture
push huggy to hub
7bf8f28 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4054653644561768,
"min": 1.4054653644561768,
"max": 1.4289926290512085,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69028.0234375,
"min": 68734.7265625,
"max": 75591.8203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 107.05970149253731,
"min": 84.73584905660377,
"max": 391.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50211.0,
"min": 48843.0,
"max": 50211.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49885.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49885.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4388246536254883,
"min": -0.0075457277707755566,
"max": 2.4679958820343018,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1143.8087158203125,
"min": -0.9583074450492859,
"max": 1410.3341064453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.710844286596343,
"min": 1.8660410419693143,
"max": 3.918502110149529,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1740.3859704136848,
"min": 236.98721233010292,
"max": 2262.5812124609947,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.710844286596343,
"min": 1.8660410419693143,
"max": 3.918502110149529,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1740.3859704136848,
"min": 236.98721233010292,
"max": 2262.5812124609947,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01558374268740105,
"min": 0.01340673443482956,
"max": 0.019286835537544296,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04675122806220315,
"min": 0.02681346886965912,
"max": 0.05633791912647818,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.047848253862725364,
"min": 0.022745518914113444,
"max": 0.0634514345890946,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14354476158817608,
"min": 0.04549103782822689,
"max": 0.19035430376728377,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3741988753000018e-06,
"min": 3.3741988753000018e-06,
"max": 0.00029533995155335004,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0122596625900005e-05,
"min": 1.0122596625900005e-05,
"max": 0.0008442984185671998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112469999999997,
"min": 0.10112469999999997,
"max": 0.19844665000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033740999999999,
"min": 0.2073953,
"max": 0.5814328,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.612253000000005e-05,
"min": 6.612253000000005e-05,
"max": 0.004922487835000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019836759000000016,
"min": 0.00019836759000000016,
"max": 0.014073496719999998,
"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": "1721793174",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"command_line_arguments": "/home/ubuntu/code/deepRL/.venv/bin/mlagents-learn ./config/ppo/huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721795479"
},
"total": 2304.586942145019,
"count": 1,
"self": 0.37778578407596797,
"children": {
"run_training.setup": {
"total": 0.025815734989009798,
"count": 1,
"self": 0.025815734989009798
},
"TrainerController.start_learning": {
"total": 2304.183340625954,
"count": 1,
"self": 4.77908742276486,
"children": {
"TrainerController._reset_env": {
"total": 2.5299960379488766,
"count": 1,
"self": 2.5299960379488766
},
"TrainerController.advance": {
"total": 2296.733125115221,
"count": 232049,
"self": 4.990765895170625,
"children": {
"env_step": {
"total": 1767.4513802572037,
"count": 232049,
"self": 1343.5453296992928,
"children": {
"SubprocessEnvManager._take_step": {
"total": 420.9120505602332,
"count": 232049,
"self": 19.064694728935137,
"children": {
"TorchPolicy.evaluate": {
"total": 401.84735583129805,
"count": 222978,
"self": 401.84735583129805
}
}
},
"workers": {
"total": 2.993999997677747,
"count": 232049,
"self": 0.0,
"children": {
"worker_root": {
"total": 2294.403110906016,
"count": 232049,
"is_parallel": true,
"self": 1251.2097004843527,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012658089981414378,
"count": 1,
"is_parallel": true,
"self": 0.00033812900073826313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009276799974031746,
"count": 2,
"is_parallel": true,
"self": 0.0009276799974031746
}
}
},
"UnityEnvironment.step": {
"total": 0.025812114006839693,
"count": 1,
"is_parallel": true,
"self": 0.0002596770063973963,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018241797806695104,
"count": 1,
"is_parallel": true,
"self": 0.00018241797806695104
},
"communicator.exchange": {
"total": 0.024824986001476645,
"count": 1,
"is_parallel": true,
"self": 0.024824986001476645
},
"steps_from_proto": {
"total": 0.0005450330208986998,
"count": 1,
"is_parallel": true,
"self": 0.00016630504978820682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00037872797111049294,
"count": 2,
"is_parallel": true,
"self": 0.00037872797111049294
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1043.1934104216634,
"count": 232048,
"is_parallel": true,
"self": 32.93879162543453,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 63.49621206586016,
"count": 232048,
"is_parallel": true,
"self": 63.49621206586016
},
"communicator.exchange": {
"total": 871.0586321542505,
"count": 232048,
"is_parallel": true,
"self": 871.0586321542505
},
"steps_from_proto": {
"total": 75.69977457611822,
"count": 232048,
"is_parallel": true,
"self": 30.201866276038345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 45.49790830007987,
"count": 464096,
"is_parallel": true,
"self": 45.49790830007987
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 524.2909789628466,
"count": 232049,
"self": 6.544957965321373,
"children": {
"process_trajectory": {
"total": 167.62587090890156,
"count": 232049,
"self": 166.14097588701406,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4848950218874961,
"count": 10,
"self": 1.4848950218874961
}
}
},
"_update_policy": {
"total": 350.12015008862363,
"count": 97,
"self": 286.9890872835531,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.13106280507054,
"count": 2910,
"self": 63.13106280507054
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4700344763696194e-06,
"count": 1,
"self": 1.4700344763696194e-06
},
"TrainerController._save_models": {
"total": 0.14113057998474687,
"count": 1,
"self": 0.0019884600187651813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1391421199659817,
"count": 1,
"self": 0.1391421199659817
}
}
}
}
}
}
}