2000 character limit reached
Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop (2404.10906v1)
Published 16 Apr 2024 in cs.AI, cs.HC, cs.LG, and cs.SC
Abstract: Embracing the pursuit of intrinsically explainable reinforcement learning raises crucial questions: what distinguishes explainability from interpretability? Should explainable and interpretable agents be developed outside of domains where transparency is imperative? What advantages do interpretable policies offer over neural networks? How can we rigorously define and measure interpretability in policies, without user studies? What reinforcement learning paradigms,are the most suited to develop interpretable agents? Can Markov Decision Processes integrate interpretable state representations? In addition to motivate an Interpretable RL community centered around the aforementioned questions, we propose the first venue dedicated to Interpretable RL: the InterpPol Workshop.
- Hindsight experience replay. Advances in neural information processing systems, 2017.
- Verifiable reinforcement learning via policy extraction. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (eds.), Advances in Neural Information Processing Systems. Curran Associates, Inc., 2018.
- A comparative study of faithfulness metrics for model interpretability methods. In Conference of the Association for Computational Linguistics (ACL), 2022.
- Use-case-grounded simulations for explanation evaluation. Advances in Neural Information Processing Systems, 2022.
- Alignnet: Unsupervised entity alignment, 2020.
- Ocatari: Object-centric atari 2600 reinforcement learning environments, 2023a.
- Interpretable and explainable logical policies via neurally guided symbolic abstraction. Advances in Neural Information Processing (NeurIPS), 2023b.
- Boosting object representation learning via motion and object continuity. In Danai Koutra, Claudia Plant, Manuel Gomez Rodriguez, Elena Baralis, and Francesco Bonchi (eds.), European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML), 2023c.
- Interpretable concept bottlenecks to align reinforcement learning agents. arXiv, 2024.
- ERASER: A benchmark to evaluate rationalized NLP models. In Conference of the Association for Computational Linguistics (ACL), 2020.
- Goal misgeneralization in deep reinforcement learning. In International Conference on Machine Learning ICML, 2022.
- Enabling risk-aware reinforcement learning for medical interventions through uncertainty decomposition. arXiv, 2021.
- gym-dssat: a crop model turned into a reinforcement learning environment, 2022.
- A survey on interpretable reinforcement learning, 2022.
- Three pathways to neurosymbolic reinforcement learning with interpretable model and policy networks. arXiv, 2024.
- A survey of methods for explaining black box models. ACM Computing Surveys, 2019.
- Efficient symbolic policy learning with differentiable symbolic expression. Advances in Neural Information Processing Systems, 2024.
- A benchmark for interpretability methods in deep neural networks. In Conference on Neural Information Processing Systems (NeurIPS), 2019.
- Symbols as a lingua franca for bridging human-ai chasm for explainable and advisable ai systems. In AAAI Conference on Artificial Intelligence, 2021.
- Objective robustness in deep reinforcement learning, 2021.
- Limits of actor-critic algorithms for decision tree policies learning in ibmdps, 2024.
- Unmasking clever hans predictors and assessing what machines really learn. Nature communications, 2019.
- Zachary Chase Lipton. The mythos of model interpretability. ArXiv, 2016.
- Insight: End-to-end neuro-symbolic visual reinforcement learning with language explanations. arXiv, 2024.
- Towards deployable rl–what’s broken with rl research and a potential fix. arXiv, 2023.
- Explainable reinforcement learning: A survey and comparative review. ACM Computing Surveys, 2023.
- Quantifying the impact of ai recommendations with explanations on prescription decision making. NPJ Digital Medicine, 2023.
- Synthetic returns for long-term credit assignment. ArXiv, 2021.
- Explainable deep learning: A field guide for the uninitiated. Journal of Artificial Intelligence Research, 2022.
- Explainability via causal self-talk. 2022.
- Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities. Knowledge-Based Systems, 2023.
- Making deep neural networks right for the right scientific reasons by interacting with their explanations. Nature Machine Intelligence, 2020.
- Optimization methods for interpretable differentiable decision trees applied to reinforcement learning. In Silvia Chiappa and Roberto Calandra (eds.), Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics. PMLR, 2020.
- Right for the right concept: Revising neuro-symbolic concepts by interacting with their explanations. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2021.
- Getting aligned on representational alignment. arXiv, 2023.
- Leveraging explanations in interactive machine learning: An overview. Frontiers in Artificial Intelligence, 2023.
- Iterative bounding mdps: Learning interpretable policies via non-interpretable methods. Proceedings of the AAAI Conference on Artificial Intelligence, 2021.
- Programmatically interpretable reinforcement learning. In International Conference on Machine Learning. PMLR, 2018.
- Read and reap the rewards: Learning to play atari with the help of instruction manuals. Advances in Neural Information Processing Systems, 2024.
- An interpretable rl framework for pre-deployment modeling in icu hypotension management. npj Digital Medicine, 2022.
- Fast segment anything, 2023.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.