Research map / Reinforcement learning / MDPs and planning
Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning
Pierriccardo Olivieri, Fausto Lasca, Alessandro Gianola, Matteo Papini
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 counterfactual reward-machine experiences (CRM) to DDPG on the product MDP (ablation) | DDPG · Parking tasks (task 1, task 2, parking 1, parking 2) | success rate | Improved |
| add HER alone to DDPG on the product MDP (ablation) | DDPG · Parking tasks | success rate | Mixed |
| combine CRM with HER (CRM-HER) instead of CRM alone (ablation) | DDPG · Parking tasks (parking 1) | success rate | Improved |
| use CRM-HER instead of plain DDPG baseline | DDPG · Parking 2 | success rate | Improved |
| use CRM-HER versus CRM on easier tasks (ablation) | DDPG · Parking task 1 and task 2 | success rate | No clear effect |
Closest papers by meaning
- On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning (ICLR 2024 · similarity 0.91)
- Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards (NeurIPS 2024 · similarity 0.88)
- DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL (ICLR 2025 · similarity 0.88)
- Regret-Free Reinforcement Learning for Temporal Logic Specifications (ICML 2025 · similarity 0.87)
- A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models (ICLR 2026 · similarity 0.87)
- Reward Machines for Deep RL in Noisy and Uncertain Environments (NeurIPS 2024 · 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.
