conftrace_

soft reinforcement learning

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

compositional sampling (1) reward structure (1) entropy-regularized reinforcement learning (1) online fine-tuning (1) goal-oriented capabilities (1) token uncertainty (1) generative flow network (1) counterfactual reasoning (1) vision-language model (1) entropy regularization (1)

Papers

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning ICML 2025 Generative Flow Networks as Entropy-Regularized RL AISTATS 2024