257 citations · 1k across the 96 of their papers we have counts for
13 papers · 1 filter
Trajectory-Refined Distillation
Li Jiang, Haoran Xu, Yichuan Ding +1
On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollout…
Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL
Sarthak Dayal, Abhinav Peri, Carl Qi +4
Hierarchical Reinforcement Learning (HRL) promises to solve long-horizon Reinforcement Learning (RL) tasks more efficiently than non-hierarchical counterparts by discovering and re…
Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
Pranaya Jajoo, Harshit Sikchi, Siddhant Agarwal +3
Behavioral Foundation Models (BFMs) produce agents with the capability to adapt to any unknown reward or task. These methods, however, are only able to produce near-optimal policie…
Unifying Agent Interaction and World Information for Multi-agent Coordination
Dongsu Lee, Daehee Lee, Yaru Niu +3
This work presents a novel representation learning framework, *interaction-world* latent (IWoL), to facilitate *team coordination* in multi-agent reinforcement learning (MARL). Bui…
Correct Reasoning Paths Visit Shared Decision Pivots
Dongkyu Cho, Amy B. Z. Zhang, Bilel Fehri +4
Chain-of-thought (CoT) reasoning exposes the intermediate thinking process of large language models (LLMs), yet verifying those traces at scale remains unsolved. In response, we in…
Information-Theoretic Reward Decomposition for Generalizable RLHF
Liyuan Mao, Haoran Xu, Amy Zhang +2
A generalizable reward model is crucial in Reinforcement Learning from Human Feedback (RLHF) as it enables correctly evaluating unseen prompt-response pairs. However, existing rewa…
MaestroMotif: Skill Design from Artificial Intelligence Feedback
Martin Klissarov, Mikael Henaff, Roberta Raileanu +7
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 m…
EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation
Carl Qi, Dan Haramati, Tal Daniel +2
Object manipulation is a common component of everyday tasks, but learning to manipulate objects from high-dimensional observations presents significant challenges. These challenges…
RLZero: Direct Policy Inference from Language Without In-Domain Supervision
Harshit Sikchi, Siddhant Agarwal, Pranaya Jajoo +6
The reward hypothesis states that all goals and purposes can be understood as the maximization of a received scalar reward signal. However, in practice, defining such a reward sign…
Automated Discovery of Functional Actual Causes in Complex Environments
Caleb Chuck, Sankaran Vaidyanathan, Stephen Giguere +3
Reinforcement learning (RL) algorithms often struggle to learn policies that generalize to novel situations due to issues such as causal confusion, overfitting to irrelevant factor…
Motif: Intrinsic Motivation from Artificial Intelligence Feedback
Martin Klissarov, Pierluca D'Oro, Shagun Sodhani +5
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…
MBRL-Lib: A Modular Library for Model-based Reinforcement Learning
Luis Pineda, Brandon Amos, Amy Zhang +2
Model-based reinforcement learning is a compelling framework for data-efficient learning of agents that interact with the world. This family of algorithms has many subcomponents th…
Composable Planning with Attributes
Amy Zhang, Adam Lerer, Sainbayar Sukhbaatar +2
The tasks that an agent will need to solve often are not known during training. However, if the agent knows which properties of the environment are important then, after learning h…