Encoding Memory in World Models with Test-Time Model-Based Reinforcement Learning
cs.LG, cs.AI, cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/burchim/TT-MBRL
Terminology
Sources
- Layer Normalization
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Soft Actor-Critic Algorithms and Applications
- Mastering Diverse Domains through World Models
- Training Agents Inside of Scalable World Models
- Test-Time Training on Nearest Neighbors for Large Language Models
- Multiplayer Interactive World Models with Representation Autoencoders
- Proximal Policy Optimization Algorithms
- DeepMind Control Suite
- Towards Accurate Generative Models of Video: A New Metric & Challenges
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