On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “NetHack”

Insights From the NeurIPS 2021 NetHack Challengecs.LG

AI agents beat previous best on NetHack, but symbolic bots still outperform.

problem Developing AI agents that can ascend in the NetHack game.

method Used a procedurally generated NetHack Learning Environment for reinforcement learning.

result Symbolic bots outperform neural approaches on NetHack.

NeurIPS NetHack Reinforcement Learning AI Symbolic AI

2022-03-22abs ↗pdf ↗

The NetHack Learning Environmentcs.LG

NetHack Learning Environment (NLE) tests RL algorithms, offering scalable, complex, and challenging gameplay.

problem Challenging environments for testing RL algorithms.

method Procedurally generated, stochastic, rich, and complex NetHack environment.

result Demonstrates empirical success for early stages of NetHack using RL.

Reinforcement Learning NetHack Learning Environment Deep RL Exploration

2020-06-24abs ↗pdf ↗

Scaling Laws for Imitation Learning in Single-Agent Gamescs.LG

Scaling up model and data size improves imitation learning in single-agent games.

problem Limited recovery of expert behavior in single-agent games using imitation learning.

method Investigate the effect of scaling model and data size on imitation learning performance.

result IL loss and mean return scale with compute budget, resulting in power laws.

Imitation Learning Scaling Laws Single-Agent Games NetHack Atari Games

2023-07-18abs ↗pdf ↗

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Researchcs.LG

MiniHack simplifies creation of complex RL environments.

problem Limited availability of challenging RL benchmarks.

method Develops a sandbox framework for easy RL environment design.

result MiniHack enables rapid creation of diverse RL testbeds.

reinforcement learning sandbox RL environments open-ended research NetHack

2021-09-27abs ↗pdf ↗

BeBold: Exploration Beyond the Boundary of Explored Regionscs.LG

BeBold improves exploration in sparse-reward tasks by regulating visitation counts.

problem Efficient exploration in deep reinforcement learning under sparse rewards.

method Regulated difference of inverse visitation counts.

result BeBold solves 12 challenging tasks in MiniGrid with fewer steps than previous state-of-the-art.

reinforcement learning exploration sparse rewards visitation counts curiosity

2020-12-15abs ↗pdf ↗