paperlist.ai

ICML 2024 Papers

International Conference on Machine Learning

202620252024202320222021202020192018201720162015

Decision breakdown

2,610papers

Counted from the official paper list; may differ slightly from the number the conference announced.

  • Oral
    1445.5%
  • Spotlight
    1917.3%
  • Poster
    2,27587.2%

Top 10 topics (click to filter)

Trends for all 207 research topics

Browse all papers

All2,610Oral144Spotlight191Poster2,275
End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations

Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li

Expand abstract

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with visual observations, but previous methods cannot refine the structured states with rewards due to a lack of efficiency. Accessibility also remains an issue, as extensive domain knowledge is required to interpret symbolic policies. In this paper, we present a neuro-symbolic framework for jointly learning structured states and symbolic policies, whose key idea is to distill the vision foundation model into an efficient perception module and refine it during policy learning. Moreover, we design a pipeline to prompt GPT-4 to generate textual explanations for the learned policies and decisions, significantly reducing users' cognitive load to understand the symbolic policies. We verify the efficacy of our approach on nine Atari tasks and present GPT-generated explanations for policies and decisions.

Spotlight
Reinforcement LearningGeneral ML · reinforcement learning
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang, Chung-Wei Lin, Chen Lv, Qi Zhu, Jürgen Schmidhuber, Chao Huang

Expand abstract

Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel *Auxiliary-Delayed Reinforcement Learning (AD-RL)* method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.

Poster
Reinforcement LearningGeneral ML · reinforcement learning