LocusRL: Diagnosing LLM Reward and Policy Interventions in Competitive Games
cs.LG
Submitted: 2026-10-03
Updated: 2026-10-03
Code: https://github.com/luancy0423/LocusRL-Pub
Sources
- Concrete Problems in AI Safety
- IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
- OpenSpiel: A Framework for Reinforcement Learning in Games
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
- Auditing language models for hidden objectives
- Spurious Rewards: Rethinking Training Signals in RLVR
- RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks