Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation

Jingbo Sun, Songjun Tu, Qichao Zhang, Haoran Li, Xin Liu +3 more
2/12/2026

No official code found. Best implementation: bofusun/DVFB (7 stars, last commit 2026-03-27).

Semantic Scholar

Code Implementations(1)

bofusun/DVFBCommunity61%

Code for "Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation", ICLR 2025 paper.

74Shell, PythonFeb 24, 20256 months ago

Similar Papers

One-Class Face Anti-Spoofing via Spoof Cue Map-Guided Feature Learning

100% match2026

Neural Multi-Objective Combinatorial Optimization via Graph-Image Multimodal Fusion

100% match2026

Long-Tail Class Incremental Learning via Independent SUb-Prototype Construction

100% match2026

Multi-View Graph Clustering via Node-Guided Contrastive Encoding

100% match2026

Probabilistic Neural Pruning via Sparsity Evolutionary Fokker-Planck-Kolmogorov Equation

99% match1 repo42026

Trusted Multi-View Classification via Evolutionary Multi-View Fusion

99% match2026

Cite this paper

@article{sun2026unsupervised,
  title  = {Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation},
  author = {Jingbo Sun and Songjun Tu and Qichao Zhang and Haoran Li and Xin Liu and Yaran Chen and Ke Chen and Dongbin Zhao},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:31c2d29fccdc99982cdb8d50ce0b919d2d38a45e},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/31c2d29fccdc99982cdb8d50ce0b919d2d38a45e.svg)](https://codeofpaper.com/paper/31c2d29fccdc99982cdb8d50ce0b919d2d38a45e)

Discussion