When to Plan: Learning to Select Between Reactive Control and Deliberative Planning
cs.AI
Submitted: 2026-07-17
Updated: 2026-10-06
Code: https://github.com/arama-Foundation/Gymnasium-Robotics
Terminology
Sources
- ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
- Learning to select computations
- Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
- Thinker: Learning to Think Fast and Slow
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Thinkless: LLM Learns When to Think
- Gemini Robotics: Bringing AI into the Physical World
- Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
- Metacontrol for Adaptive Imagination-Based Optimization
- When Can Model-Free Reinforcement Learning be Enough for Thinking?
- All-in-One: A DRL-based Control Switch Combining State-of-the-art Navigation Planners
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- Zero-Overhead Introspection for Adaptive Test-Time Compute
- RouteLLM: Learning to Route LLMs with Preference Data
- OpenAI o1 System Card
- Toward Agents That Reason About Their Computation
- Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
- Rational Metareasoning for Large Language Models
- Proximal Policy Optimization Algorithms
- Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems