5 papers
A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
Yu Lei, Minghuan Liu, Abhiram Maddukuri +2
Co-training, which combines limited in-domain real-world data with abundant surrogate data such as simulation or cross-embodiment robot data, is widely used for training generative…
The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
Seth Karten, Jake Grigsby, Tersoo Upaa +28
We present the PokeAgent Challenge, a large-scale benchmark for decision-making research built on Pokemon's multi-agent battle system and expansive role-playing game (RPG) environm…
DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
Changyeon Kim, Haeone Lee, Younggyo Seo +2
Offline reinforcement learning (RL) presents an attractive paradigm for training intelligent agents without expensive online interactions. However, current approaches still struggl…
Human-Level Competitive Pokémon via Scalable Offline Reinforcement Learning with Transformers
Jake Grigsby, Yuqi Xie, Justin Sasek +2
Competitive Pokémon Singles (CPS) is a popular strategy game where players learn to exploit their opponent based on imperfect information in battles that can last more than one hu…
VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making
Jake Grigsby, Yuke Zhu, Michael Ryoo +1
Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. V…