With opponent-action feedback in zero-sum games, an efficient algorithm achieves near-optimal t^{-1/2} last-iterate convergence in duality gap with high probability.
nature , volume=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
ATD(λ) adapts TD(λ) in MARL via a density ratio estimator on past/current replay buffers to assign λ per state-action pair, yielding competitive or better results than fixed-λ QMIX and MAPPO on SMAC and Gfootball.
LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
NonZero introduces an interaction score and bandit-formalized proposal rule for local agent deviations in multi-agent MCTS, delivering a sublinear local-regret guarantee and improved sample efficiency on game benchmarks without full joint-action enumeration.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
Muon optimizer with weight decay and update scaling achieves ~2x efficiency over AdamW for large LLMs, shown via the Moonlight 3B/16B MoE model trained on 5.7T tokens.
Longer action horizons bottleneck LLM agent training through instability, but training with reduced horizons stabilizes learning and enables better generalization to longer horizons.
citing papers explorer
-
Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
With opponent-action feedback in zero-sum games, an efficient algorithm achieves near-optimal t^{-1/2} last-iterate convergence in duality gap with high probability.
-
Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
-
Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning
ATD(λ) adapts TD(λ) in MARL via a density ratio estimator on past/current replay buffers to assign λ per state-action pair, yielding competitive or better results than fixed-λ QMIX and MAPPO on SMAC and Gfootball.
-
Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
-
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
-
NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
NonZero introduces an interaction score and bandit-formalized proposal rule for local agent deviations in multi-agent MCTS, delivering a sublinear local-regret guarantee and improved sample efficiency on game benchmarks without full joint-action enumeration.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
-
Muon is Scalable for LLM Training
Muon optimizer with weight decay and update scaling achieves ~2x efficiency over AdamW for large LLMs, shown via the Moonlight 3B/16B MoE model trained on 5.7T tokens.
-
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
Longer action horizons bottleneck LLM agent training through instability, but training with reduced horizons stabilizes learning and enables better generalization to longer horizons.