keypapers

Key Papers in Deep RL

What follows is a list of papers in deep RL that are worth reading. This is far from comprehensive, but should provide a useful starting point for someone looking to do research in the field.

:depth: 2

1. Model-Free RL

a. Deep Q-Learning

b. Policy Gradients

c. Deterministic Policy Gradients

d. Distributional RL

e. Policy Gradients with Action-Dependent Baselines

f. Path-Consistency Learning

g. Other Directions for Combining Policy-Learning and Q-Learning

h. Evolutionary Algorithms

1. Exploration

a. Intrinsic Motivation

b. Unsupervised RL

1. Transfer and Multitask RL

2. Hierarchy

3. Memory

4. Model-Based RL

a. Model is Learned

b. Model is Given

1. Meta-RL

2. Scaling RL

3. RL in the Real World

4. Safety

5. Imitation Learning and Inverse Reinforcement Learning

6. Reproducibility, Analysis, and Critique

7. Bonus: Classic Papers in RL Theory or Review