Research map / Reinforcement learning / MDPs and planning
Exact Reduction of Huge Action Spaces in General Reinforcement Learning
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 |
|---|---|---|---|
| Sequentialize and binarize the action space before applying ESA | ESA · General environments | surrogate-MDP state-space upper bound: \left(\frac{2}{\eps (1-\g)^3}\right)^{\abs{\A}} -> \frac{4\ceil{1 - \g + \lb\abs{\A}}^6}{\g^2 \eps^2 (1-\g)^6} | Helped |
| Sequentialize actions into binary decisions with the discount factor chosen so that \lambda^d = \g | General reinforcement learning processes · General environments | near-optimality preservation: \lambda^{d-1}\eps -> \eps | Helped |
| Augment observations with partial decision vectors during sequentialization | MDPs · MDPs over \O | Markov property preservation | Helped |
Closest papers by meaning
- Oracle-Efficient Reinforcement Learning for Max Value Ensembles (NeurIPS 2024 · similarity 0.88)
- Sleeping Reinforcement Learning (ICML 2025 · similarity 0.88)
- Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping (ICLR 2024 · similarity 0.88)
- In-Context Reinforcement Learning for Variable Action Spaces (ICML 2024 · similarity 0.87)
- Action abstractions for amortized sampling (ICLR 2025 · similarity 0.86)
- How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach (NeurIPS 2024 · similarity 0.86)
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.