Faynt: Scaling and Optimizing Policies for Competitive Melee
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning
- Training Compute-Optimal Large Language Models
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- GLU Variants Improve Transformer
- Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
- Attention Residuals
- Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models
- MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
- Distilling the Knowledge in a Neural Network
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
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