https://github.com/debmandal/RL-Causality
References at the Intersection of Causality and Reinforcement Learning
https://github.com/debmandal/RL-Causality
reference
Last synced: 11 months ago
JSON representation
References at the Intersection of Causality and Reinforcement Learning
- Host: GitHub
- URL: https://github.com/debmandal/RL-Causality
- Owner: debmandal
- Created: 2018-12-05T22:48:39.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2020-08-19T18:52:28.000Z (over 5 years ago)
- Last Synced: 2024-11-01T00:31:46.971Z (over 1 year ago)
- Topics: reference
- Homepage:
- Size: 16.6 KB
- Stars: 88
- Watchers: 10
- Forks: 10
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-interesting-topics-in-nlp - RL
- awesome-causality-in-nlp - RL-Causality
- awesome-causal-ai - RL-Causality - References at the Intersection of Causality and Reinforcement Learning *(Unknown)* (🚀 GitHub Repositories / 🌟 **Real-World Magic**)
README
I aim to review and understand how causal inference can be helpful in making reinforcement learning better. I think causality can make RL more sample efficient, make it interpretable and broaden its range of applications.
# Papers at the Intersection of Reinforcement Learning and Causal Inference
* [Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search](https://openreview.net/forum?id=BJG0voC9YQ), Under Review, *ICLR*, 2019.
* [Causal Reasoning from Meta-Reinforcement Learning](https://openreview.net/forum?id=H1ltQ3R9KQ), Under Review, *ICLR*, 2019.
* [Discovering Latent Causes in Reinforcement Learning](https://www.princeton.edu/~nivlab/papers/GershmanNormanNiv2015.pdf), Gershman et al., *Behavioral Sciences*, 2015.
* [Reinforcement Learning and Cauasl Models](http://gershmanlab.webfactional.com/pubs/RL_causal.pdf), Sam Gershman, 2016.
* [Representation Balancing MDPs for Off-Policy Policy Evaluation](https://arxiv.org/pdf/1805.09044.pdf), Liu et. al., *NeurIPS*, 2018.
* [Learning Plannable Representation with Causal InfoGAN](https://arxiv.org/pdf/1807.09341.pdf), Kurutach et al., *PAL*, 2018.
* [High-Confidence Policy Improvement](https://people.cs.umass.edu/~pthomas/papers/Thomas2015b.pdf), Thomas et al., *ICML*, 2015.
## Relevant RL Papers
* [Learning Model Based Planning from Scratch](https://arxiv.org/pdf/1707.06170.pdf), Pascanu et al., *arxiv*, 2017.
* [An Introduction to Deep Reinforcement Learning](https://arxiv.org/pdf/1811.12560.pdf), Francois-Lavet et al., *arxiv*, 2018.
* [Combined Reinforcement Learning via Abstract Representations](https://arxiv.org/abs/1809.04506), Francois-Lavet et al., *arxiv*, 2018.
* [TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning](https://arxiv.org/abs/1710.11417), Farquhar et al., *arxiv*, 2018.
* [Hindsight Experience Replay](https://papers.nips.cc/paper/7090-hindsight-experience-replay.pdf), Andrychowicz et al., *NIPS*, 2017.
* [Universal Value Function Approximator](http://proceedings.mlr.press/v37/schaul15.pdf), Schaul et al., *ICML*, 2015.
* [Continuous Control with Deep Reinforcement Learning](https://arxiv.org/pdf/1509.02971.pdf), Lillicrap et al., *ICLR*, 2016.