Research map / Reinforcement learning / Policy gradient and actor-critic
Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control
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 action descriptors in DDPG instead of directly outputting a high-dimensional action vector | DDPG · PDE Model | mean reward per episode | Helped |
| Use action descriptors in DDPG instead of directly outputting a high-dimensional action vector | DDPG · Heat Invader | mean reward per episode | Helped |
| Use separate neural networks for each action component instead of a shared descriptor-conditioned policy | DDPG with Action Descriptors · PDE Model | sample efficiency | Helped |
| Use separate neural networks for each action component instead of a shared descriptor-conditioned policy | DDPG with Action Descriptors · Heat Invader | mean reward per episode | Hurt |
| Use only one action dimension | Heat Invader control algorithms · Heat Invader | mean reward per episode | Hurt |
Closest papers by meaning
- Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces (ICLR 2025 · similarity 0.88)
- Model-based Reinforcement Learning for Parameterized Action Spaces (ICML 2024 · similarity 0.86)
- A Differential and Pointwise Control Approach to Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction (ICLR 2025 · similarity 0.86)
- Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control (ICLR 2025 · similarity 0.85)
- Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking (NeurIPS 2024 · 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.