action space
The set of all possible actions or decisions that an AI agent can take in a specific environment or problem domain, often delineated in reinforcement learning contexts to define the choices available to the agent at each step.
- $O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
- FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
- LLM-PySC2: Starcraft II learning environment for Large Language Models
- Learning to Clean: Reinforcement Learning for Noisy Label Correction
- Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning
- Meta-learning how to Share Credit among Macro-Actions
- Non-Stationary Lipschitz Bandits
- Quantization-Free Autoregressive Action Transformer
- Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems
- Theoretical Guarantees for the Retention of Strict Nash Equilibria by Coevolutionary Algorithms
- VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning