Research map / Reinforcement learning / Visual and representation RL
LeDeepChef Deep Reinforcement Learning Agent for Families of Text-Based Games
Leonard Adolphs, Thomas Hofmann
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 |
|---|---|---|---|
| Prune the admissible command set | Random command selection · TextWorld Challenge valid and test | points per game (%): 11.7 -> 33.5; 12.8 -> 39.6 | Improved |
| Prune the admissible command set | DRRN · TextWorld Challenge valid and test | points per game (%): 14.0 -> 34.3; 13.2 -> 44.1 | Improved |
| Use LeDeepChef rather than DRRN Pruned | DRRN Pruned · TextWorld Challenge valid and test | points per game (%): 34.3 -> 74.4; 44.1 -> 69.3 | Improved |
| Use LeDeepChef rather than the curriculum DQN baseline | Curriculum DQN [cite] · Validation games | points per game (%): 58 -> 74.4 | Improved |
Closest papers by meaning
- Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games (NeurIPS 2020 · similarity 0.88)
- RL-GPT: Integrating Reinforcement Learning and Code-as-policy (NeurIPS 2024 · similarity 0.86)
- BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games (ICLR 2025 · similarity 0.86)
- Monte Carlo Planning with Large Language Model for Text-Based Game Agents (ICLR 2025 · similarity 0.85)
- AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents (NeurIPS 2026 · similarity 0.85)
- Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs (NeurIPS 2025 · 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.
