/cs294-112_hws

My solution to assignments in UC Berkeley CS294-112: Deep Reinforcement Learning

Primary LanguagePythonMIT LicenseMIT

CS294-112: Deep Reinforcement Learning (UC Berkeley; Fall 2018)

My solution to assignments in UC Berkeley CS294-112: Deep Reinforcement Learning (Fall 2018). All results, including reports and instructions to exactly reproduce my experiments, are in the README.md under each homework folder.

  • Assignment 1: Imitation Learning (done)
  • Assignment 2: Policy Gradients (done)
  • Assignment 3: Q-Learning and Actor-Critic (done)
  • Assignment 4: Model-Based Reinforcement Learning (done)
  • Assignment 5
    • HW5a: Exploration (done)
    • HW5b: Soft Actor-Critic (done)
    • HW5c: Meta-Reinforcement Learning (done)