Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.
hub
Liar” ends the game, then both players reveal their dice. If the last bid is not satisfied, then the player who called “Liar
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Proves CLS-hardness for Nash equilibrium computation in two-team polymatrix games with zero-sum or coordination pairwise payoffs, with tight CLS membership when one team has independent adversaries, plus an ε-Nash algorithm with 1/ε² runtime dependence.
GenBR uses MCTS and generative models for scalable best responses in multiagent settings, applied within PSRO using bargaining theory to build opponent models, achieving human-comparable performance in Deal-or-No-Deal negotiations.
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
A neuron-astrocyte network with dual-timescale memory reduces median path lengths up to sixfold in partially observable grid-world navigation tasks.
CivBench trains models on turn-level states in Civilization V to predict victory probabilities, providing a progress-based evaluation of LLM strategic capabilities across 307 games with 7 models.
AReaL decouples generation and training in LLM reinforcement learning to achieve up to 2.77x speedup with matched or better performance on math and code benchmarks.
ARROW adds a distribution-matching long-term replay buffer to DreamerV3 and shows reduced forgetting versus same-size baselines on Atari and Procgen continual RL benchmarks.
An open-sourced Unified Autonomy Stack fuses LiDAR, radar, vision and inertial data with sampling-based planning and control barrier functions to deliver resilient autonomy on aerial and ground robots in challenging real-world settings.
The chapter synthesizes the history of adaptive learning systems and examines how AI can provide instructional intelligence and real-time adaptivity in serious games while highlighting challenges such as explainability and limited long-term outcome data.
citing papers explorer
-
Generative Agents: Interactive Simulacra of Human Behavior
Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.
-
The Complexity of Two-Team Polymatrix Games with Independent Adversaries
Proves CLS-hardness for Nash equilibrium computation in two-team polymatrix games with zero-sum or coordination pairwise payoffs, with tight CLS membership when one team has independent adversaries, plus an ε-Nash algorithm with 1/ε² runtime dependence.
-
Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning
GenBR uses MCTS and generative models for scalable best responses in multiagent settings, applied within PSRO using bargaining theory to build opponent models, achieving human-comparable performance in Deal-or-No-Deal negotiations.
-
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
-
Dual-Timescale Memory in a Spiking Neuron-Astrocyte Network for Efficient Navigation
A neuron-astrocyte network with dual-timescale memory reduces median path lengths up to sixfold in partially observable grid-world navigation tasks.
-
CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V
CivBench trains models on turn-level states in Civilization V to predict victory probabilities, providing a progress-based evaluation of LLM strategic capabilities across 307 games with 7 models.
-
AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
AReaL decouples generation and training in LLM reinforcement learning to achieve up to 2.77x speedup with matched or better performance on math and code benchmarks.
-
ARROW: Augmented Replay for RObust World models
ARROW adds a distribution-matching long-term replay buffer to DreamerV3 and shows reduced forgetting versus same-size baselines on Atari and Procgen continual RL benchmarks.
-
The Unified Autonomy Stack: Toward a Blueprint for Generalizable Robot Autonomy
An open-sourced Unified Autonomy Stack fuses LiDAR, radar, vision and inertial data with sampling-based planning and control barrier functions to deliver resilient autonomy on aerial and ground robots in challenging real-world settings.
-
AI-Enabled Serious Games: Integrating Intelligence and Adaptivity in Training Systems
The chapter synthesizes the history of adaptive learning systems and examines how AI can provide instructional intelligence and real-time adaptivity in serious games while highlighting challenges such as explainability and limited long-term outcome data.