CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs
cs.AI
Submitted: 2026-02-10
Updated: 2026-11-16
Code: https://github.com/ax-ml/jax
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- SIMA 2: A Generalist Embodied Agent for Virtual Worlds
- ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
- Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
- Benchmarking the Spectrum of Agent Capabilities
- Open-Endedness is Essential for Artificial Superhuman Intelligence
- MaestroMotif: Skill Design from Artificial Intelligence Feedback
- Adaptive Reward Design for Reinforcement Learning
- The NetHack Learning Environment
- Code as Policies: Language Model Programs for Embodied Control
- Eurekaverse: Environment Curriculum Generation via Large Language Models
- Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling
- LLM Augmented Hierarchical Agents
- Proximal Policy Optimization Algorithms
- Human-Timescale Adaptation in an Open-Ended Task Space
- Code as Reward: Empowering Reinforcement Learning with VLMs
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
- Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents