← curriculum/phase 9 · Reinforcement Learning
edit on github ↗
← all lessons in phase
phase 9 · 12 lessons
  • 01Mdps States Actions Rewards
  • 02Dynamic Programming
  • 03Monte Carlo Methods
  • 04Q Learning Sarsa
  • 05Dqn
  • 06Policy Gradients Reinforce
  • 07Actor Critic A2c A3c
  • 08Ppo
  • 09Reward Modeling Rlhf
  • 10Multi Agent Rl
  • 11Sim To Real Transfer
  • 12Rl For Games
‹
›
phase 9 · lesson 05 of 12

Dqn

05-dqn·full lesson folder ↗

← previous
Q Learning Sarsa
complete & next →
Policy Gradients Reinforce
Edit with