danorel's picture
Pushing PPO Snowball algorithm
c8d7434
raw
history blame contribute delete
No virus
18.4 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9906752109527588,
"min": 0.9906752109527588,
"max": 2.8735220432281494,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9491.6591796875,
"min": 9491.6591796875,
"max": 29427.73828125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.926616668701172,
"min": 0.33151811361312866,
"max": 12.926616668701172,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.690185546875,
"min": 64.31451416015625,
"max": 2610.86328125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06709454748459964,
"min": 0.06148246275918555,
"max": 0.07286617564215489,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26837818993839857,
"min": 0.2459298510367422,
"max": 0.3643308782107745,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2294520766419523,
"min": 0.11297991221734122,
"max": 0.293161410443923,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9178083065678092,
"min": 0.45191964886936487,
"max": 1.4658070522196152,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.75,
"min": 3.090909090909091,
"max": 25.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 136.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 3.090909090909091,
"max": 25.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 136.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1693144520",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1693145008"
},
"total": 488.79723151,
"count": 1,
"self": 0.5797519709999506,
"children": {
"run_training.setup": {
"total": 0.052798604000031446,
"count": 1,
"self": 0.052798604000031446
},
"TrainerController.start_learning": {
"total": 488.16468093500004,
"count": 1,
"self": 0.5673830589997237,
"children": {
"TrainerController._reset_env": {
"total": 4.564703056000042,
"count": 1,
"self": 4.564703056000042
},
"TrainerController.advance": {
"total": 482.77962142500024,
"count": 18224,
"self": 0.29901532901601513,
"children": {
"env_step": {
"total": 482.48060609598423,
"count": 18224,
"self": 351.6447621549781,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.47547361700106,
"count": 18224,
"self": 1.8092623810021564,
"children": {
"TorchPolicy.evaluate": {
"total": 128.6662112359989,
"count": 18224,
"self": 128.6662112359989
}
}
},
"workers": {
"total": 0.36037032400508906,
"count": 18224,
"self": 0.0,
"children": {
"worker_root": {
"total": 486.5800996489937,
"count": 18224,
"is_parallel": true,
"self": 226.6270784629968,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005470402000014474,
"count": 1,
"is_parallel": true,
"self": 0.00395708299998887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015133190000256036,
"count": 10,
"is_parallel": true,
"self": 0.0015133190000256036
}
}
},
"UnityEnvironment.step": {
"total": 0.09761391499995398,
"count": 1,
"is_parallel": true,
"self": 0.0006605189999504546,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003768589999708638,
"count": 1,
"is_parallel": true,
"self": 0.0003768589999708638
},
"communicator.exchange": {
"total": 0.0944228550000048,
"count": 1,
"is_parallel": true,
"self": 0.0944228550000048
},
"steps_from_proto": {
"total": 0.0021536820000278567,
"count": 1,
"is_parallel": true,
"self": 0.00037319499989507676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00178048700013278,
"count": 10,
"is_parallel": true,
"self": 0.00178048700013278
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 259.95302118599693,
"count": 18223,
"is_parallel": true,
"self": 10.985348587996441,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.41532663500152,
"count": 18223,
"is_parallel": true,
"self": 5.41532663500152
},
"communicator.exchange": {
"total": 205.7853056210078,
"count": 18223,
"is_parallel": true,
"self": 205.7853056210078
},
"steps_from_proto": {
"total": 37.76704034199116,
"count": 18223,
"is_parallel": true,
"self": 7.091083906974518,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.675956435016644,
"count": 182230,
"is_parallel": true,
"self": 30.675956435016644
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014448199999606004,
"count": 1,
"self": 0.00014448199999606004,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 479.0273258060352,
"count": 454056,
"is_parallel": true,
"self": 10.088909882045357,
"children": {
"process_trajectory": {
"total": 263.5661567269896,
"count": 454056,
"is_parallel": true,
"self": 262.15951554498974,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4066411819998734,
"count": 4,
"is_parallel": true,
"self": 1.4066411819998734
}
}
},
"_update_policy": {
"total": 205.37225919700023,
"count": 90,
"is_parallel": true,
"self": 78.44907751700157,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.92318167999866,
"count": 4587,
"is_parallel": true,
"self": 126.92318167999866
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2528289130000303,
"count": 1,
"self": 0.001176365999981499,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2516525470000488,
"count": 1,
"self": 0.2516525470000488
}
}
}
}
}
}
}