model name : Intel(R) Core(TM) i7-7700 CPU @ 3.60GHz
CPU MHz : 1600.004
cache size : 8192 KB
GPU: NVIDIA Corporation GP104 [GeForce GTX 1080] (rev a1)
ubuntu18.04 + GPU 驅動 + cuda 10 + cudnn 7.4:
參考之前已經在虛擬機上實現的安裝配置流程:
在此再寫一遍的目的主要是為瞭記錄下新踩的那些坑:
2. mujocopy 安裝後,一直報錯,主要原因是,由於下載的是最新的mujoco_py版本,因此在set_up文件中已經將mujoco的版本設定為瞭最新的2.1.1,所以之前下載的200以及210版本均無法識別,因此下載最新的mujoco版本後,問題解決,mujoco_py實現瞭編譯:
3. D4RL的安裝問題,也是由於無法找到指定的.h文件,從而無法實現安裝,解決思路:一個一個包安裝,下載dm-control安裝後,再安裝d4rl:
4.依照項目說明,完成配置:
運行命令:mopo run_local examples.development --config=examples.config.d4rl.halfcheetah_mixed --gpus=1 --trial-gpus=1
運行截圖:
eb35a76519f9be090afd78abcd341358
example: 具體應用的offlineRL例子 文件夾
mopo: 具體的算法設定文件夾
ray_mopo:用於存儲結果的文件夾
softlearning:構建RL模型的工具包,Softlearning is a deep reinforcement learning toolbox for training maximum entropy policies in continuous domains.The implementation is fairly thin and primarily optimized for our own development purposes.It utilizes the tf.keras modules for most of the model classes(e.g.policies and value functions).We use Ray for the experiment orchestration.Ray Tune and Autoscaler implement several neat features that enable us to seamlessly run the same experiment scripts that we use for local prototyping to launch large-scale experiments on any chosen cloud service(e.g.GCP or AWS),and intelligently parallelize and distribute training for effective resource allocation.
上一篇