A Unified Taxonomy and Evaluation Framework for Distributional Shifts in Reinforcement Learning
cs.LG, cs.AI
Submitted: 2026-06-15
Updated: 2026-11-09
Terminology
Sources
- Concrete Problems in AI Safety
- A Tutorial on Meta-Reinforcement Learning
- RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
- A Survey of State Representation Learning for Deep Reinforcement Learning
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Assessing the Impact of Distribution Shift on Reinforcement Learning Performance
- Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model
- Towards Out-Of-Distribution Generalization: A Survey
- Sample-Efficient Reinforcement Learning of Partially Observable Markov Games
- A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points
- Mitigating Distribution Shift in Model-based Offline RL via Shifts-aware Reward Learning
- Playing Atari with Deep Reinforcement Learning
- Evaluation-Time Policy Switching for Offline Reinforcement Learning
- Assessing Generalization in Deep Reinforcement Learning
- An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks
- Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning
- Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
- Robust Visual Domain Randomization for Reinforcement Learning
- A Study on Overfitting in Deep Reinforcement Learning
- Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey
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