InfoTree casts intermediate state selection in tree search as monotone submodular maximization under fixed rollout budgets, yielding closed-form UUCB terms and lifting mixed-outcome ratios while outperforming flat GRPO and prior tree variants on nine benchmarks.
MIT press, 2018
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Establishes last-iterate convergence rates for on-policy Q-learning under minimal irreducibility assumptions, with sample complexity O(1/ξ²) matching off-policy up to exploration factors.
GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
DiPRL trains nearly discrete programmatic policies in RL by adding architecture entropy regularization to gradient-based optimization, avoiding performance collapse from post-hoc discretization.
citing papers explorer
-
Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
InfoTree casts intermediate state selection in tree search as monotone submodular maximization under fixed rollout budgets, yielding closed-form UUCB terms and lifting mixed-outcome ratios while outperforming flat GRPO and prior tree variants on nine benchmarks.
-
A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies
Establishes last-iterate convergence rates for on-policy Q-learning under minimal irreducibility assumptions, with sample complexity O(1/ξ²) matching off-policy up to exploration factors.
-
Group-in-Group Policy Optimization for LLM Agent Training
GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
-
DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy Regularization
DiPRL trains nearly discrete programmatic policies in RL by adding architecture entropy regularization to gradient-based optimization, avoiding performance collapse from post-hoc discretization.