policy learning
Policy learning is an aspect of reinforcement learning where an agent learns to make decisions by mapping states of the environment to actions. A policy can be deterministic or stochastic and is essential for enabling an agent to achieve goals through interaction with its environment.
- 3D Equivariant Visuomotor Policy Learning via Spherical Projection
- A Practical Guide for Incorporating Symmetry in Diffusion Policy
- Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning
- Bridging Equivariant GNNs and Spherical CNNs for Structured Physical Domains
- EconGym: A Scalable AI Testbed with Diverse Economic Tasks
- Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives
- Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions
- HCRMP: An LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving
- LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward Search
- Learning 3D Persistent Embodied World Models
- Learning Interactive World Model for Object-Centric Reinforcement Learning
- Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
- Object-centric 3D Motion Field for Robot Learning from Human Videos
- Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
- STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
- Social World Model-Augmented Mechanism Design Policy Learning
- To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL
- Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper