# A Novel Approach to Curiosity and Explainable Reinforcement Learning via Interpretable Sub-Goals

arXiv: https://arxiv.org/abs/2104.06630 · HTML: https://mlsanity.com/paper/2104.06630/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 22 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 17 of 17)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Benchmarking Deep Reinforcement Learning for Continuous Control](https://mlsanity.com/paper/1604.06778/) (2016)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Large-Scale Study of Curiosity-Driven Learning](https://mlsanity.com/paper/1808.04355/) (2018)
- [Modular Multitask Reinforcement Learning with Policy Sketches](https://mlsanity.com/paper/1611.01796/) (2016)
- [Explainable Reinforcement Learning Through a Causal Lens](https://mlsanity.com/paper/1905.10958/) (2019)
- [Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation](https://mlsanity.com/paper/1903.10992/) (2019)
- [Learning with AMIGo: Adversarially Motivated Intrinsic Goals](https://mlsanity.com/paper/2006.12122/) (2020)
- [TorchBeast: A PyTorch Platform for Distributed RL](https://mlsanity.com/paper/1910.03552/) (2019)
- [Maximum-Likelihood Augmented Discrete Generative Adversarial Networks](https://mlsanity.com/paper/1702.07983/) (2017)
- [Learning and Exploiting Multiple Subgoals for Fast Exploration in Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1905.05180/) (2019)

## Built on by (most cited first, 2 of 2)

- [Structure in Deep Reinforcement Learning: A Survey and Open Problems](https://mlsanity.com/paper/2306.16021/) (2023)
- [Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications](https://mlsanity.com/paper/2207.01911/) (2022)

## Abstract (arXiv)

Two key challenges within Reinforcement Learning involve improving (a) agent learning within environments with sparse extrinsic rewards and (b) the explainability of agent actions. We describe a curious subgoal focused agent to address both these challenges. We use a novel method for curiosity produced from a Generative Adversarial Network (GAN) based model of environment transitions that is robust to stochastic environment transitions. Additionally, we use a subgoal generating network to guide navigation. The explainability of the agent's behavior is increased by decomposing complex tasks into a sequence of interpretable subgoals that do not require any manual design. We show that this method also enables the agent to solve challenging procedurally-generated tasks that contain stochastic transitions above other state-of-the-art methods.