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
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.
Forward citations
Cited by 6 Pith papers
-
Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
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.
-
Agent Learning via Early Experience
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...
-
CoEx -- Co-evolving World-model and Exploration
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...
-
Structured Feedback Improves Repair in an LLM Agent Loop
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...
-
Learning to Reason for Factuality
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.
-
Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation
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.
Discussion (0). Sign in to comment.