Continual Reinforcement Learning Is an Integration Problem
cs.LG
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: 39 pages, 2 figures, 5 tables. Playable companion and source code: https://github.com/fractalbrain-ai/10d-game
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Definition of AGI
- Measuring Progress Toward AGI: A Cognitive Framework
- Progressive Neural Networks
- PathNet: Evolution Channels Gradient Descent in Super Neural Networks
- Adaptive Computation Time for Recurrent Neural Networks
- Neural Turing Machines
- Unsupervised Predictive Memory in a Goal-Directed Agent
- Forager: a lightweight testbed for continual learning with partial observability in RL
- World Action Models are Zero-shot Policies
- Causally Correct Partial Models for Reinforcement Learning
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Rethinking Reflection in Pre-Training
- Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
- The Cell Must Go On: Agar.io for Continual Reinforcement Learning
- ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
- On the Measure of Intelligence
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