Papers NetHack
“NetHack” 태그가 달린 논문 28편 · 필터 해제
MaestroMotif: Skill Design from Artificial Intelligence Feedback
Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an AI system. We present MaestroMotif, a method for AI-assisted skill design, whic…
Code GenerationDecision MakingNetHackBALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities, however, they still struggle to perform well in complex, dynamic environments. Real-wo…
BenchmarkingNetHackSpatial ReasoningSyllabus: Portable Curricula for Reinforcement Learning Agents
Curriculum learning has been a quiet yet crucial component of many of the high-profile successes of reinforcement learning. Despite this, none of the major reinforcement learning libraries directly support curriculum lea…
NetHackreinforcement-learningReinforcement LearningOnline Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback
Automatically synthesizing dense rewards from natural language descriptions is a promising paradigm in reinforcement learning (RL), with applications to sparse reward problems, open-ended exploration, and hierarchical sk…
Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+2PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice
You have an environment, a model, and a reinforcement learning library that are designed to work together but don't. PufferLib makes them play nice. The library provides one-line environment wrappers that eliminate commo…
NetHackreinforcement-learningReinforcement LearningPlaying NetHack with LLMs: Potential & Limitations as Zero-Shot Agents
Large Language Models (LLMs) have shown great success as high-level planners for zero-shot game-playing agents. However, these agents are primarily evaluated on Minecraft, where long-term planning is relatively straightf…
Decision MakingMinecraftNetHackCraftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms. We identify that existing benchmarks used for research into open-ended learning fall into one of two categories. E…
GPUMinecraftNetHackreinforcement-learning+2Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills
Large language models (LLMs) have recently been used for sequential decision making in interactive environments. However, leveraging environment reward signals for continual LLM actor improvement is not straightforward. …
Decision MakingLanguage ModelingLanguage ModellingNetHack+1Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models. However, fine-tuning reinforcement learning…
Montezuma's RevengeNetHackreinforcement-learningReinforcement Learning (RL)diff History for Neural Language Agents
Neural Language Models (LMs) offer an exciting solution for general-purpose embodied control. However, a key technical issue arises when using an LM-based controller: environment observations must be converted to text, w…
Decision MakingNetHackSequence-to-sequence Language ModelingMotif: Intrinsic Motivation from Artificial Intelligence Feedback
Exploring rich environments and evaluating one's actions without prior knowledge is immensely challenging. In this paper, we propose Motif, a general method to interface such prior knowledge from a Large Language Model (…
Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+2Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors
Large language models (LLMs) are being applied as actors for sequential decision making tasks in domains such as robotics and games, utilizing their general world knowledge and planning abilities. However, previous work …
Decision MakingLanguage ModelingLanguage ModellingNetHack+2Scaling Laws for Imitation Learning in Single-Agent Games
Imitation Learning (IL) is one of the most widely used methods in machine learning. Yet, many works find it is often unable to fully recover the underlying expert behavior, even in constrained environments like single-ag…
Atari GamesImitation LearningNetHackLuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents
In the last few decades we have witnessed a significant development in Artificial Intelligence (AI) thanks to the availability of a variety of testbeds, mostly based on simulated environments and video games. Among those…
NetHackKatakomba: Tools and Benchmarks for Data-Driven NetHack
NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions. One of the promising directions for a breakthrough is using pre-collected d…
D4RLNetHackRecommendation Systemsreinforcement-learning+1Accelerating exploration and representation learning with offline pre-training
Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement learning (RL) algorithms address this challenge by improved credit assignment, intr…
Decision MakingNetHackReinforcement Learning (RL)Representation Learning+1Dungeons and Data: A Large-Scale NetHack Dataset
Recent breakthroughs in the development of agents to solve challenging sequential decision making problems such as Go, StarCraft, or DOTA, have relied on both simulated environments and large-scale datasets. However, pro…
Decision MakingNetHackOffline RLSequential Decision Making+1Improving Policy Learning via Language Dynamics Distillation
Recent work has shown that augmenting environments with language descriptions improves policy learning. However, for environments with complex language abstractions, learning how to ground language to observations is dif…
NetHackReinforcement Learning (RL)Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. Instead, they are usually trained end-to-end, with the hope being tha…
Inductive BiasNetHackreinforcement-learningReinforcement Learning+1Insights From the NeurIPS 2021 NetHack Challenge
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' in) the popular dungeon-crawler game of N…
NetHackReinforcement Learning (RL)