A Bird's-Eye View of Iterative Reward Design
cs.LG, cs.AI, cs.RO
Submitted: 2026-10-03
Updated: 2026-10-03
Code: https://github.com/safety-research/bird
Sources
- Concrete Problems in AI Safety
- Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo
- Hyperspherical Normalization for Scalable Deep Reinforcement Learning
- Evolution through Large Models
- Illuminating search spaces by mapping elites
- Proximal Policy Optimization Algorithms
- FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks