How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents

• URL: http://arxiv.org/abs/2002.08795v1
• Date: Wed, 19 Feb 2020 17:18:20 GMT
• Title: How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents
• Authors: Prithviraj Ammanabrolu, Ethan Tien, Zhaochen Luo, Mark O. Riedl
• Abstract summary: We introduce two new game state exploration strategies for text-based games. We compare our exploration strategies against strong baselines on the classic text-adventure game, Zork1.
• Score: 17.215984752298443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-based games -- in which an agent interacts with the world through textual natural language -- present us with the problem of combinatorially-sized action-spaces. Most current reinforcement learning algorithms are not capable of effectively handling such a large number of possible actions per turn. Poor sample efficiency, consequently, results in agents that are unable to pass bottleneck states, where they are unable to proceed because they do not see the right action sequence to pass the bottleneck enough times to be sufficiently reinforced. Building on prior work using knowledge graphs in reinforcement learning, we introduce two new game state exploration strategies. We compare our exploration strategies against strong baselines on the classic text-adventure game, Zork1, where prior agent have been unable to get past a bottleneck where the agent is eaten by a Grue.

Related papers

• A Minimal Approach for Natural Language Action Space in Text-based Games [103.21433712630953]
  This paper revisits the challenge of exploring the action space in text-based games (TGs) We propose $ epsilon$-admissible exploration, a minimal approach of utilizing admissible actions, for training phase. We present a text-based actor-critic (TAC) agent that produces textual commands for game, solely from game observations.
  arXiv  Detail & Related papers  (2023-05-06T16:05:27Z)
• Are AlphaZero-like Agents Robust to Adversarial Perturbations? [73.13944217915089]
  AlphaZero (AZ) has demonstrated that neural-network-based Go AIs can surpass human performance by a large margin. We ask whether adversarial states exist for Go AIs that may lead them to play surprisingly wrong actions. We develop the first adversarial attack on Go AIs that can efficiently search for adversarial states by strategically reducing the search space.
  arXiv  Detail & Related papers  (2022-11-07T18:43:25Z)
• Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games [64.11746320061965]
  We study reinforcement learning for text-based games, which are interactive simulations in the context of natural language. We aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. We extensively evaluate our method on a number of man-made benchmark games, and the experimental results demonstrate that our method performs better than existing text-based agents.
  arXiv  Detail & Related papers  (2020-10-22T12:40:22Z)
• How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds [16.626095390308304]
  We introduce Q*BERT, an agent that learns to build a knowledge graph of the world by answering questions. We further introduce MC!Q*BERT an agent that uses a knowledge-graph-based intrinsic motivation to detect bottlenecks. We present an ablation study and results demonstrating how our method outperforms the current state-of-the-art on nine text games.
  arXiv  Detail & Related papers  (2020-06-12T18:24:06Z)
• Efficient exploration of zero-sum stochastic games [83.28949556413717]
  We investigate the increasingly important and common game-solving setting where we do not have an explicit description of the game but only oracle access to it through gameplay. During a limited-duration learning phase, the algorithm can control the actions of both players in order to try to learn the game and how to play it well. Our motivation is to quickly learn strategies that have low exploitability in situations where evaluating the payoffs of a queried strategy profile is costly.
  arXiv  Detail & Related papers  (2020-02-24T20:30:38Z)
• Learning Dynamic Belief Graphs to Generalize on Text-Based Games [55.59741414135887]
  Playing text-based games requires skills in processing natural language and sequential decision making. In this work, we investigate how an agent can plan and generalize in text-based games using graph-structured representations learned end-to-end from raw text.
  arXiv  Detail & Related papers  (2020-02-21T04:38:37Z)
• Exploration Based Language Learning for Text-Based Games [72.30525050367216]
  This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games. Text-based computer games describe their world to the player through natural language and expect the player to interact with the game using text. These games are of interest as they can be seen as a testbed for language understanding, problem-solving, and language generation by artificial agents.
  arXiv  Detail & Related papers  (2020-01-24T03:03:51Z)

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.