YSU RL HW

Created
Created
2024 Mar 6 1:24
Creator
Creator
Seonglae ChoSeonglae Cho
Editor
Edited
Edited
2024 Nov 18 22:8
Refs
Refs
7 HW, only count top 6
Discussion is fine, copy is not allowed (list up all names of collaborators)

Plan

  1. Imitation learning
  1. Actor critic algorithms
  1. Q learning algorithms
  1. On policy RL algorithm
  1. Model-based RL
  1. Offline RL
  1. RLHF

Changed detail

  1. Behavior cloning & Dagger (Imitation learning)
  1. Policy Gradient & PPO (Policy Gradient & Actor critic algorithms)
  1. DQN (Q learning)
  1. SAC (Soft actor critic)
    1. CQL (Offline-RL)
  1. (Model-based) Dreamer
YSU RL HWs
 

Render

export DEBIAN_FRONTEND=noninteractive apt-get update apt-get install -y libosmesa6-dev libgl1-mesa-glx libglfw3 libgl1-mesa-dev libglew-dev patchelf ffmpeg conda install -c conda-forge gcc=12.1.0 conda install pyopengl
 
 
 
 
 

Recommendations