SPRING: Studying the Paper and Reasoning to Play Games

• URL: http://arxiv.org/abs/2305.15486v3
• Date: Mon, 11 Dec 2023 22:18:51 GMT
• Title: SPRING: Studying the Paper and Reasoning to Play Games
• Authors: Yue Wu, Shrimai Prabhumoye, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Tom Mitchell, Yuanzhi Li
• Abstract summary: We propose a novel approach, SPRING, to read the game's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM) In experiments, we study the quality of in-context "reasoning" induced by different forms of prompts under the setting of the Crafter open-world environment. Our experiments suggest that LLMs, when prompted with consistent chain-of-thought, have great potential in completing sophisticated high-level trajectories.
• Score: 102.5587155284795
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel approach, SPRING, to read the game's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM). Prompted with the LaTeX source as game context and a description of the agent's current observation, our SPRING framework employs a directed acyclic graph (DAG) with game-related questions as nodes and dependencies as edges. We identify the optimal action to take in the environment by traversing the DAG and calculating LLM responses for each node in topological order, with the LLM's answer to final node directly translating to environment actions. In our experiments, we study the quality of in-context "reasoning" induced by different forms of prompts under the setting of the Crafter open-world environment. Our experiments suggest that LLMs, when prompted with consistent chain-of-thought, have great potential in completing sophisticated high-level trajectories. Quantitatively, SPRING with GPT-4 outperforms all state-of-the-art RL baselines, trained for 1M steps, without any training. Finally, we show the potential of games as a test bed for LLMs.

Related papers

• A Survey on Large Language Model-Based Game Agents [9.892954815419452]
  The development of game agents holds a critical role in advancing towards Artificial General Intelligence (AGI) This paper provides a comprehensive overview of LLM-based game agents from a holistic viewpoint.
  arXiv  Detail & Related papers  (2024-04-02T15:34:18Z)
• EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning [23.83162741035859]
  We present EXPLORER, which is an exploration-guided reasoning agent for textual reinforcement learning. Our experiments show that EXPLORER outperforms the baseline agents on Text-World cooking (TW-Cooking) and Text-World Commonsense (TWC) games.
  arXiv  Detail & Related papers  (2024-03-15T21:22:37Z)
• GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations [87.99872683336395]
  Large Language Models (LLMs) are integrated into critical real-world applications. This paper evaluates LLMs' reasoning abilities in competitive environments. We first propose GTBench, a language-driven environment composing 10 widely recognized tasks.
  arXiv  Detail & Related papers  (2024-02-19T18:23:36Z)
• DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent) [73.10899129264375]
  This paper explores DoraemonGPT, a comprehensive and conceptually elegant system driven by LLMs to understand dynamic scenes. Given a video with a question/task, DoraemonGPT begins by converting the input video into a symbolic memory that stores task-related attributes. We extensively evaluate DoraemonGPT's effectiveness on three benchmarks and several in-the-wild scenarios.
  arXiv  Detail & Related papers  (2024-01-16T14:33:09Z)
• ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents [77.34720446306419]
  Alympics is a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research. Alympics creates a versatile platform for studying complex game theory problems.
  arXiv  Detail & Related papers  (2023-11-06T16:03:46Z)
• Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning [65.36326734799587]
  We present a novel subgame curriculum learning framework for zero-sum games. It adopts an adaptive initial state distribution by resetting agents to some previously visited states. We derive a subgame selection metric that approximates the squared distance to NE values.
  arXiv  Detail & Related papers  (2023-10-07T13:09:37Z)
• Generalization in Text-based Games via Hierarchical Reinforcement Learning [42.70991837415775]
  We introduce a hierarchical framework built upon the knowledge graph-based RL agent. In the high level, a meta-policy is executed to decompose the whole game into a set of subtasks specified by textual goals. In the low level, a sub-policy is executed to conduct goal-conditioned reinforcement learning.
  arXiv  Detail & Related papers  (2021-09-21T05:27:33Z)
• The NetHack Learning Environment [79.06395964379107]
  We present the NetHack Learning Environment (NLE), a procedurally generated rogue-like environment for Reinforcement Learning research. We argue that NetHack is sufficiently complex to drive long-term research on problems such as exploration, planning, skill acquisition, and language-conditioned RL. We demonstrate empirical success for early stages of the game using a distributed Deep RL baseline and Random Network Distillation exploration.
  arXiv  Detail & Related papers  (2020-06-24T14:12:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.