MAC-v2: Long-horizon model-based value expansion from pixels
cs.LG, cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Project page: https://kwanyoungpark.github.io/MAC-v2/ABSTRACT
Terminology
Sources
- Offline Reinforcement Learning with Universal Horizon Models
- Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations
- Mastering Atari with Discrete World Models
- Training Agents Inside of Scalable World Models
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
- Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- Decoupled Q-Chunking
- Reinforcement Learning with Action Chunking
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- Being-H0.7: A Latent World-Action Model from Egocentric Videos
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Playing Atari with Deep Reinforcement Learning
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
- Horizon Reduction Makes RL Scalable
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- Chunk-Guided Q-Learning
- Learning Latent Dynamic Robust Representations for World Models
- From Pixels to Torques: Policy Learning with Deep Dynamical Models
- Behavior Regularized Offline Reinforcement Learning
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