Permanent and Transient Representations for Continual Reinforcement Learning
cs.LG, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/NishanthVAnand/pt_representations_crl
Terminology
Sources
- Plasticity as the Mirror of Empowerment
- Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning
- Streaming Deep Reinforcement Learning Finally Works
- Simplifying Deep Temporal Difference Learning
- FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff
- Plasticity Loss in Deep Reinforcement Learning: A Survey
- Learning Continually by Spectral Regularization
- Adaptive Online Planning for Continual Lifelong Learning
- Understanding and Preventing Capacity Loss in Reinforcement Learning
- Disentangling the Causes of Plasticity Loss in Neural Networks
- Self-Composing Policies for Scalable Continual Reinforcement Learning
- Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
- Playing Atari with Deep Reinforcement Learning
- A Survey of Continual Reinforcement Learning
- The Alberta Plan for AI Research
- MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
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