Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Eye of the Beholder: Improved Relation Generalization for Text-Based Reinforcement Learning Agents
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add image features to the text-only agent | SceneIT · TWC Test IN and OUT | normalized score | Helped |
| Add image features to the text-only agent | SceneIT · FTWP Cooking Task | normalized score | Mixed |
| Add image features to the text-only agent | SceneIT · Jericho selected games | maximum score | Helped |
| Use finetuned AttnGAN image generation rather than retrieved or pretrained AttnGAN images (ablation) | SceneIT · TWC difficulty levels, IN and OUT | normalized score | Helped |
| Use images from internet retrieval instead of finetuned AttnGAN (ablation) | SceneIT · FTWP Cooking Task | normalized score | No clear effect |
Closest papers by meaning
- Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning (ICLR 2026 · similarity 0.86)
- BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games (ICLR 2025 · similarity 0.86)
- Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning (ICML 2024 · similarity 0.85)
- Learning Multi-Object Positional Relationships via Emergent Communication (AAAI 2024 · similarity 0.85)
- Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision (NeurIPS 2025 · similarity 0.85)
- Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play (ICLR 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.