Skip to content
conftrace_

policy refinement

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

self-evolving memory (1) adaptive planning (1) large language model (1) safety specification (1) counter-example guided (1) output refinement (1) in-context reward hacking (1) vision-and-language navigation (1) negative side effect (1) gradient-based update (1)

Papers

NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments ICCV 2025 Feedback Loops With Language Models Drive In-Context Reward Hacking ICML 2024 Counterexample Guided RL Policy Refinement Using Bayesian Optimization NeurIPS 2021