My notes on (in my opinion) important reinforcement learning papers.
Typo corrections, additional points, paper suggestions etc are all very welcome. You can either make a pull request or email me at einet89[at]postech.ac.kr
| Date | Contents |
|---|---|
| 2016/10/11 | DQN, DDQN, Prioritized Experience Replay, Dueling Network |
| 2016/12/27 | Value Iteration Networks, The Predictron |
| 2017/05/29 | Stochastic Computation Graphs |
| 2017/07/12 | Evolution Strategies |
| 2017/08/09 | Modular Multitask RL with Policy Sketches |
| 2017/09/14 | Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks |
| 2017/10/17 | Continuous Adaptation vie Meta-Learning in Nonstationary and Competitive Environments |
| 2017/11/02 | Parameter Space Noise for Exploration |
| 2017/12/19 | Meta Learning Shared Hierarchies |