herurg's picture
Hugging Face Deep RL Course Unit 5 - SnowballTarget PPO 200k steps
290f989 verified
Raw
History Blame Contribute Delete
18.6 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9301773309707642,
"min": 0.9301773309707642,
"max": 2.8548381328582764,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8901.796875,
"min": 8901.796875,
"max": 29236.3984375,
"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": 13.029752731323242,
"min": 0.4599590003490448,
"max": 13.029752731323242,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2540.8017578125,
"min": 89.23204803466797,
"max": 2655.13330078125,
"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": 0.06632330234695509,
"min": 0.05825561663942947,
"max": 0.0732825357873819,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26529320938782036,
"min": 0.23302246655771788,
"max": 0.36558282253855734,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18379654399320192,
"min": 0.1082863658461172,
"max": 0.2770290133999843,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7351861759728077,
"min": 0.4331454633844688,
"max": 1.3851450669999217,
"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": 25.227272727272727,
"min": 3.3181818181818183,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 146.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.3181818181818183,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 146.0,
"max": 1428.0,
"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": "1787484777",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/content/mlagents310/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --results-dir=/content/drive/MyDrive/HF_DeepRL_Unit5/SnowballTarget/results --no-graphics",
"mlagents_version": "1.1.0",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1787485462"
},
"total": 685.2451881649995,
"count": 1,
"self": 1.1227142569987336,
"children": {
"run_training.setup": {
"total": 0.03725851600029273,
"count": 1,
"self": 0.03725851600029273
},
"TrainerController.start_learning": {
"total": 684.0852153920005,
"count": 1,
"self": 0.800374903870761,
"children": {
"TrainerController._reset_env": {
"total": 1.5195302889987943,
"count": 1,
"self": 1.5195302889987943
},
"TrainerController.advance": {
"total": 681.5624041181309,
"count": 18205,
"self": 0.37987620601415983,
"children": {
"env_step": {
"total": 681.1825279121167,
"count": 18205,
"self": 567.0195842240901,
"children": {
"SubprocessEnvManager._take_step": {
"total": 113.72894640095001,
"count": 18205,
"self": 2.0427400068765564,
"children": {
"TorchPolicy.evaluate": {
"total": 111.68620639407345,
"count": 18205,
"self": 111.68620639407345
}
}
},
"workers": {
"total": 0.433997287076636,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 679.3559382000276,
"count": 18205,
"is_parallel": true,
"self": 258.53809170599743,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003471994001301937,
"count": 1,
"is_parallel": true,
"self": 0.0011892059992533177,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002282788002048619,
"count": 10,
"is_parallel": true,
"self": 0.002282788002048619
}
}
},
"UnityEnvironment.step": {
"total": 0.05059065000023111,
"count": 1,
"is_parallel": true,
"self": 0.0008530070008418988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046413600102823693,
"count": 1,
"is_parallel": true,
"self": 0.00046413600102823693
},
"communicator.exchange": {
"total": 0.045732892998785246,
"count": 1,
"is_parallel": true,
"self": 0.045732892998785246
},
"steps_from_proto": {
"total": 0.0035406139995757258,
"count": 1,
"is_parallel": true,
"self": 0.0008110050002869684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027296089992887573,
"count": 10,
"is_parallel": true,
"self": 0.0027296089992887573
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 420.81784649403016,
"count": 18204,
"is_parallel": true,
"self": 17.734258205033257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.532736267008659,
"count": 18204,
"is_parallel": true,
"self": 8.532736267008659
},
"communicator.exchange": {
"total": 330.49337325894885,
"count": 18204,
"is_parallel": true,
"self": 330.49337325894885
},
"steps_from_proto": {
"total": 64.0574787630394,
"count": 18204,
"is_parallel": true,
"self": 11.5002919646613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 52.5571867983781,
"count": 182040,
"is_parallel": true,
"self": 52.5571867983781
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00023700099882262293,
"count": 1,
"self": 0.00023700099882262293,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 677.0200500372193,
"count": 543432,
"is_parallel": true,
"self": 12.164619660397875,
"children": {
"process_trajectory": {
"total": 382.31853930981924,
"count": 543432,
"is_parallel": true,
"self": 381.2012408298215,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1172984799977712,
"count": 4,
"is_parallel": true,
"self": 1.1172984799977712
}
}
},
"_update_policy": {
"total": 282.5368910670022,
"count": 90,
"is_parallel": true,
"self": 72.79886204503055,
"children": {
"TorchPPOOptimizer.update": {
"total": 209.73802902197167,
"count": 4587,
"is_parallel": true,
"self": 209.73802902197167
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.20266908000121475,
"count": 1,
"self": 0.012905108002087218,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18976397199912753,
"count": 1,
"self": 0.18976397199912753
}
}
}
}
}
}
}