Pith. sign in

REVIEW 6 cited by

TextWorld: A Learning Environment for Text-based Games

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1806.11532 v2 pith:6S6C7K7P submitted 2018-06-29 cs.LG cs.CLstat.ML

classification cs.LGcs.CLstat.ML
keywords gameslearningtextworldtext-basedagentschallengescuratedenvironment
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose features and challenges we have analyzed. More significantly, it enables users to handcraft or automatically generate new games. Its generative mechanisms give precise control over the difficulty, scope, and language of constructed games, and can be used to relax challenges inherent to commercial text games like partial observability and sparse rewards. By generating sets of varied but similar games, TextWorld can also be used to study generalization and transfer learning. We cast text-based games in the Reinforcement Learning formalism, use our framework to develop a set of benchmark games, and evaluate several baseline agents on this set and the curated list.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Modeling agent trajectories as action-centric probabilistic graphs lets a GNN warn LLM agents of likely step-level errors before execution, improving pass ratio ~14.7% across four benchmarks.

  2. Agent Learning via Early Experience

    cs.AI 2025-10 conditional novelty 6.0 of 10

    Training agents to predict consequences of their own alternative actions (implicit world modeling) or to reflect on why expert actions were better (self-reflection) consistently improves task success, OOD generalizati...

  3. CoEx -- Co-evolving World-model and Exploration

    cs.AI 2025-07 conditional novelty 6.0 of 10

    CoEx co-evolves an LLM agent's subgoal planning with an explicit, neurosymbolic belief state that is updated after each subgoal attempt, leading to improved success rates on ALFWorld, PDDL, and Jericho compared to sev...

  4. Structured Feedback Improves Repair in an LLM Agent Loop

    cs.SE 2026-07 conditional novelty 5.0 of 10

    Verifier feedback that includes the failed location, observed value, and valid alternatives substantially improves LLM repair success in TextWorld; most of the gain comes from the alternatives rather than from JSON fo...

  5. Learning to Reason for Factuality

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    An online RL reward balancing factual precision, detail, and relevance is reported to reduce reasoning-LLM hallucination by 23.1 points, but the attached manuscript is an unrelated paper.

  6. Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation

    cs.CL 2025-06 conditional novelty 3.0 of 10

    A thesis proposal repurposing two prior papers on LM agents for text games, framed as a path to theory-of-mind AI, with no new theory-of-mind evidence.

Pith tools