conftrace_

self-supervised reinforcement learning

6 papers

Explore in graph

Also known as

SSRL

Co-occurring keywords · papers mentioning both

reinforcement learning with verifiable reward (2) pretext task (2) goal-reaching policy (1) state coverage (1) maximum-entropy goal distribution (1) skill repertoire (1) interactive fiction (1) unified multimodal model (1) multi-constraint instruction (1) text-based game (1)

Papers

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following ACL 2026 Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models CVPR 2026 Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning CVPR 2026 VideoSSR: Video Self-Supervised Reinforcement Learning CVPR 2026 STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models ACL 2024 Skew-Fit: State-Covering Self-Supervised Reinforcement Learning ICML 2020