Teaching Agents the "Principle", Not the "Reward": Prescriptive Policy Learning
cs.LG
Submitted: 2026-11-04
Updated: 2026-11-07
Terminology
Sources
- OpenAI Gym
- Soft Actor-Critic for Discrete Action Settings
- Leveraging Procedural Generation to Benchmark Reinforcement Learning
- Informativeness of Reward Functions in Reinforcement Learning
- Proximal Policy Optimization Algorithms
- Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis