conftrace_

soft bellman equation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multi-step reasoning (1) rényi divergence (1) credit assignment (1) risk-sensitive control (1) soft actor-critic (1) maximum entropy control (1) renyi divergence (1) value function (1) policy gradient (1) variational inference (1)

Papers

Offline Reinforcement Learning for LLM Multi-step Reasoning ACL 2025 Risk-sensitive control as inference with Rényi divergence NeurIPS 2024