CS 285: Lecture 13, Part 3 - YouTube
youtube.com · 2,663 words · saved by 1 readers
Follow along using the transcript. Follow along using the transcript. New New New New New
all right next let's talk about some actual exploration algorithms that we could use in deep reinforcement learning so to recap the classes of exploration methods that we have our optimistic exploration which basically say that visiting a new state is a good thing this requires estimating uh some kind of state visitation frequency or novelty just like we had to count the number of times that we took each action in the bandit setting and this is typically realized by means of some kind of exploration bonus we have thompson sampling style algorithms so these are algorithms that learn a…
saved by
related reading
- CS 285: Lecture 13, Part 2youtube.com
- A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
- Part 1: Key Concepts in RL - Spinning Up documentationspinningup.openai.com
- Part 3: Intro to Policy Optimization - Spinning Up documentationspinningup.openai.com
- The Multi-Armed Bandit Problem and Its Solutions | Lil'Loglilianweng.github.io
- Reinforcement Learning: Machine Learning Meets Control Theoryyoutube.com
- Exploration Strategies in Deep Reinforcement Learning | Lil'Loglilianweng.github.io
- Part 2: Kinds of RL Algorithms - Spinning Up documentationspinningup.openai.com
- RL_Notes__final_.pdfjubayer-ibn-hamid.github.io
- Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
- RLAlgsInMDPs.pdfsites.ualberta.ca
- course_stat_rl.pdfmit.edu