Behavior-Discriminative Reward Shaping for Reward-Robust Reinforcement Learning
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/ZixuanLiu4869/reward_shaping
Terminology
Sources
- Enhancing LLM Safety via Constrained Direct Preference Optimization
- Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts
- Maximum Entropy RL (Provably) Solves Some Robust RL Problems
- Improving the Effectiveness of Potential-Based Reward Shaping in Reinforcement Learning
- BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping
- Dual Formulation for Non-Rectangular Lp Robust Markov Decision Processes
- State Entropy Regularization for Robust Reinforcement Learning
- Proximal Policy Optimization Algorithms
- OpenAI Gym
- Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
- Three Mechanisms of Weight Decay Regularization
- Reward-Robust RLHF in LLMs
- Robust General Utility for Reinforcement Learning
- Lightning Does Not Strike Twice: Robust MDPs with Coupled Uncertainty
- A unified view of entropy-regularized Markov decision processes
- Robust Learning with Jacobian Regularization
- Marginalized State Distribution Entropy Regularization in Policy Optimization
- Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures
- Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning
- Dota 2 with Large Scale Deep Reinforcement Learning
Related papers
- 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
- (Mis)generalization of Helpful-Only Fine-tuning