HadrienCr's picture
Deep RL Course 2nd try
bea9dcd verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.0896008014678955,
"min": 2.0896008014678955,
"max": 2.8781380653381348,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 21307.66015625,
"min": 20771.3203125,
"max": 29475.01171875,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 5.565084457397461,
"min": 0.17080172896385193,
"max": 5.565084457397461,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1135.2772216796875,
"min": 33.135536193847656,
"max": 1135.2772216796875,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 13.8,
"min": 3.1363636363636362,
"max": 13.8,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 759.0,
"min": 138.0,
"max": 759.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 13.8,
"min": 3.1363636363636362,
"max": 13.8,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 759.0,
"min": 138.0,
"max": 759.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.077521520225798,
"min": 0.06467075724332758,
"max": 0.077521520225798,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.155043040451596,
"min": 0.12934151448665515,
"max": 0.20724409716814418,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.28602686633958535,
"min": 0.11679404042882538,
"max": 0.28602686633958535,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5720537326791707,
"min": 0.23358808085765076,
"max": 0.7956818916341837,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999992e-05,
"min": 1.6464094511999992e-05,
"max": 0.00028046400651199994,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2928189023999985e-05,
"min": 3.2928189023999985e-05,
"max": 0.0005839921053360001,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10548799999999997,
"min": 0.10548799999999997,
"max": 0.19348800000000005,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.21097599999999994,
"min": 0.21097599999999994,
"max": 0.4946640000000001,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0046750512,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005677024,
"min": 0.0005677024,
"max": 0.009743733600000004,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1719035000",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719035231"
},
"total": 231.1935535309999,
"count": 1,
"self": 0.42512272800013307,
"children": {
"run_training.setup": {
"total": 0.05121374600003037,
"count": 1,
"self": 0.05121374600003037
},
"TrainerController.start_learning": {
"total": 230.71721705699974,
"count": 1,
"self": 0.313961196010041,
"children": {
"TrainerController._reset_env": {
"total": 2.1678631690001566,
"count": 1,
"self": 2.1678631690001566
},
"TrainerController.advance": {
"total": 228.1420507909893,
"count": 9136,
"self": 0.13254497699517742,
"children": {
"env_step": {
"total": 228.0095058139941,
"count": 9136,
"self": 157.48329376299944,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.39158679798129,
"count": 9136,
"self": 0.6971241959809049,
"children": {
"TorchPolicy.evaluate": {
"total": 69.69446260200039,
"count": 9136,
"self": 69.69446260200039
}
}
},
"workers": {
"total": 0.13462525301338246,
"count": 9136,
"self": 0.0,
"children": {
"worker_root": {
"total": 230.01476085700733,
"count": 9136,
"is_parallel": true,
"self": 120.64642620004179,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020915219997732493,
"count": 1,
"is_parallel": true,
"self": 0.0006469720001405221,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014445499996327271,
"count": 10,
"is_parallel": true,
"self": 0.0014445499996327271
}
}
},
"UnityEnvironment.step": {
"total": 0.03532054499964943,
"count": 1,
"is_parallel": true,
"self": 0.0006808919997638441,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038987700008874526,
"count": 1,
"is_parallel": true,
"self": 0.00038987700008874526
},
"communicator.exchange": {
"total": 0.03237776700007089,
"count": 1,
"is_parallel": true,
"self": 0.03237776700007089
},
"steps_from_proto": {
"total": 0.0018720089997259493,
"count": 1,
"is_parallel": true,
"self": 0.0003487399994810403,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001523269000244909,
"count": 10,
"is_parallel": true,
"self": 0.001523269000244909
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 109.36833465696554,
"count": 9135,
"is_parallel": true,
"self": 4.979603768009383,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.6678287209888367,
"count": 9135,
"is_parallel": true,
"self": 2.6678287209888367
},
"communicator.exchange": {
"total": 85.64176659998293,
"count": 9135,
"is_parallel": true,
"self": 85.64176659998293
},
"steps_from_proto": {
"total": 16.079135567984395,
"count": 9135,
"is_parallel": true,
"self": 2.954485399956411,
"children": {
"_process_rank_one_or_two_observation": {
"total": 13.124650168027983,
"count": 91350,
"is_parallel": true,
"self": 13.124650168027983
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002983570002470515,
"count": 1,
"self": 0.0002983570002470515,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 224.79246962912157,
"count": 420750,
"is_parallel": true,
"self": 8.413199142081794,
"children": {
"process_trajectory": {
"total": 148.7846739390393,
"count": 420750,
"is_parallel": true,
"self": 148.46090210403918,
"children": {
"RLTrainer._checkpoint": {
"total": 0.32377183500011597,
"count": 2,
"is_parallel": true,
"self": 0.32377183500011597
}
}
},
"_update_policy": {
"total": 67.59459654800048,
"count": 22,
"is_parallel": true,
"self": 23.149594113990588,
"children": {
"TorchPPOOptimizer.update": {
"total": 44.44500243400989,
"count": 2241,
"is_parallel": true,
"self": 44.44500243400989
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09304354400001102,
"count": 1,
"self": 0.0009155469997494947,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09212799700026153,
"count": 1,
"self": 0.09212799700026153
}
}
}
}
}
}
}