Learning When to Think: Adaptive Internal Computation for Reinforcement Learning
cs.LG, cs.RO
Submitted: 2026-11-07
Updated: 2026-11-07
Project page: https://rohitsalla.github.io/aic-neurips2026
Terminology
Sources
- PonderNet: Learning to Ponder
- OpenAI Gym
- Universal Transformers
- TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- On the Role of Computation in Reinforcement Learning
- Adaptive Computation Time for Recurrent Neural Networks
- Metacontrol for Adaptive Imagination-Based Optimization
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
- Selecting Computations: Theory and Applications
- Multi-Scale Dense Networks for Resource Efficient Image Classification
- On the importance of single directions for generalization
- Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
- Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
- D3P: Dynamic Denoising Diffusion Policy via 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