Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents
cs.LG, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/mpSchrader/gym-sokoban
Sources
- Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning
- Reinforcement Learning for Long-Horizon Interactive LLM Agents
- Post-training Large Language Models for Diverse High-Quality Responses
- GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
- Modifying Large Language Model Post-Training for Diverse Creative Writing
- Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization
- Diversity is All You Need: Learning Skills without a Reward Function
- Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
- Group-in-Group Policy Optimization for LLM Agent Training
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
- VinePPO: Refining Credit Assignment in RL Training of LLMs
- Diverse Preference Optimization
- The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
- LIMR: Less is More for RL Scaling
- Understanding R1-Zero-Like Training: A Critical Perspective
- Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies
- Non-local Policy Optimization via Diversity-regularized Collaborative Exploration
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