Research map / Reinforcement learning / Visual and representation RL
A Composable Specification Language for Reinforcement Learning Tasks
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 |
|---|---|---|---|
| Use a task monitor to provide subtask progress and memory to the policy | Spectrl · Specifications φ5, φ6, and φ7 | probability of satisfying the specification | Helped |
| Remove reward shaping (ablation) | Spectrl · Specifications with sequencing, especially φ5, φ6, and φ7 | probability of satisfying the specification | Hurt |
| Use reward shaping | Spectrl · Specifications φ1–φ7 | convergence | Helped |
| Add multiple constraints, including obstacle avoidance and a fuel constraint | CCE · φ2 | probability of satisfying the specification | Hurt |
| Use Spectrl instead of TLTL | Spectrl and TLTL · φ1 and φ4 | convergence | Helped |
| Use Spectrl instead of TLTL | Spectrl and TLTL · Cartpole | convergence | Helped |
| Use Spectrl instead of CCE | Spectrl and CCE · Cartpole | probability of satisfying the specification | Helped |
Closest papers by meaning
- Text2Reward: Reward Shaping with Language Models for Reinforcement Learning (ICLR 2024 · similarity 0.89)
- Progress Reward Model for Reinforcement Learning via Large Language Models (NeurIPS 2025 · similarity 0.89)
- HYPRL: Reinforcement Learning of Control Policies for Hyperproperties (NeurIPS 2025 · similarity 0.88)
- On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning (ICLR 2024 · similarity 0.87)
- Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution (AAAI 2025 · similarity 0.87)
- R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models (ICML 2025 · similarity 0.87)
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.