The paper explores a runtime strategy-selection framework where a large language model (LLM) guides a pre‑trained reinforcement learning (RL) policy for non‑player characters (NPCs) in a Unity combat game without altering the underlying policy. Five NPC agents sharing a PPO policy were compared in a baseline setup and an LLM‑augmented setup, where a locally hosted Mistral 7B model assigns one of four tactical tags every five seconds based on live game state. Across 600 episodes against three scripted opponents, the LLM‑augmented agents more than doubled their win rate against a Balanced opponent, improved performance against an Evasive opponent, but struggled against an Aggressive opponent due to over‑reliance on encirclement; analysis of 2,430 strategy selections revealed limited zero‑shot differentiation with the model favoring Surround in 83.8% of cases.
arXiv:2609.38881v1 Announce Type: new Abstract: Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and att...
arXiv:2606. 20014v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies.
The paper presents a constrained command‑conditioned Proximal Policy Optimization (PPO) executor for the MicroRTS real‑time strategy environment, enabling a single execution policy to follow diverse strategic commands. A Thompson‑sampling bandit strategist selects command tuples based on in‑game observations of the opponent’s strategy, rather than relying on opponent identity. In controlled experiments, the strategist‑executor system outperforms a flat PPO baseline against three of the four strongest opponents on a training map, including two held‑out opponents, while showing no significant difference against the remaining opponents.
The paper introduces Adversarial Heuristic Learning (AHL), a framework that uses AI agents to refine game policies without changing model weights. It presents AAArena, a benchmark of 12 adversarial games and 1,920 human programs, where agents analyze replays, select opponents, and revise policies to maximize ranking within limited budgets. Experiments show that certain configurations achieve gold medals, while performance drops in games with complex rules, highlighting challenges in game understanding and long‑horizon policy development.
The paper introduces Porimon, an LLM-based agent for Pokémon Battles that uses Long/Short-Term Knowledge Augmented Generation (LSTKAG) to incorporate past states of the current task and retrieve experience summaries from similar previous instances. Porimon also employs an external API for precise damage calculation and detailed game information. Experimental results from 15,000 simulated battles show that Porimon, with hyperparameter optimization, outperforms both the earlier PokéLLMon agent and a rule-based heuristic player, and ablation studies confirm the benefit of the game information retrieval extension, though the impact of Long-Term KAG remains inconclusive.
arXiv:2608. 06735v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution.
The paper introduces CASTLE, a framework for fully decentralized multi‑agent reinforcement learning that uses two offline‑trained world models to provide in‑context guidance to independent agents. A Local Dynamics World Model captures each agent’s trajectory dynamics, while a Semantic‑Social World Model predicts short‑horizon task and social outcomes for candidate actions based on counterfactual simulator rollouts. During online learning, these frozen models supply prediction logits to an independent PPO policy, enabling agents to compare potential actions prospectively rather than relying solely on scalar rewards. CASTLE outperforms existing baselines on several multi‑particle benchmark tasks, achieving the highest mean final scores across 30 seeds.
The paper presents a decentralized navigation framework for composite heterogeneous robots that integrates a large language model (LLM) policy agent, an Upper Confidence Bound (UCB) bandit, and a Double Deep Q-Network (Double DQN) controller. Each robot independently generates and refines policies at the round level using LLM inference, while the Double DQN handles tick-level action selection based on navigation variables and LLM priors. Across 30 rounds, the full configuration achieved all goals with the lowest median completion time (42 ticks) and a 25–39% improvement over other setups.
arXiv:2606. 00017v1 Announce Type: new Abstract: Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decisions made by other players.
arXiv:2610.18354v1 Announce Type: new Abstract: Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capabil...
The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.
The paper introduces DUOS, a meta‑learned update rule for shaping opponents in general‑sum games. Unlike prior methods that require access to an opponent’s parameters or learning dynamics, DUOS learns a rule that maximises an agent’s expected return using only its own experience. Experiments show the discovered rule behaves like opponent shaping and achieves top performance in tournament settings.