Policy Gradient Methods

REINFORCE, actor-critic, advantage estimation and GAE, the PPO idea.

0 / 5 solved

Question Tags Difficulty Success

1. Score Function Sleight of Hand

reinforcepolicy-gradient +1

Medium —

2. The Baseline That Bites Back

baselineadvantage-function +1

Medium —

3. Farming The Shaping Reward

reinforcement-learningreward-shaping +2

Hard —

4. Lambda's Balancing Act

actor-criticgae +1

Medium —

5. The Clip That Keeps You Honest

ppoclipped-objective +1

Hard —

Learning Resources

OpenAI, Spinning Up in Deep RL

Up next

5 of 5 questions here are still unsolved.

Next in ML in Other Domains Natural Language Processing