1 citations · 1 across the 18 of their papers we have counts for
29 papers
Training Controllable World Models via Action Influence Maximization
Samuel M. Bateman, Tenny Yin, Chongyi Zheng +5
Action-conditioned video generative models trained on successful, goal-directed demonstrations tend to ignore the commanded action, rendering a plausible expert-like future regardl…
Measuring Empowerment from Offline Data for Intrinsically Motivated Exploration
Ishir Garg, Vivek Myers, Qiyang Li +3
Large, unlabeled datasets of prior experience have become increasingly available for agentic tasks in domains such as robotics and coding. A common recipe for these tasks is to tra…
Two Perfect One-Factorizations of
Tomasz Maciosowski
A perfect 1-factorization of the complete graph is a partition of its edges into perfect matchings such that the union of any two of them is a Hamilton cycle. Kotzig conje…
Scaling Empowered Agents
Catherine Ji, Vivek Myers, Joshua Lin +3
Empowerment measures the capacity of an agent to actively control its environment. In this work, we explain the connection between skill learning and empowerment. While skill learn…
The Geometry of Empowerment
Catherine Ji, Vivek Myers, Sergey Levine +1
Empowerment captures the capacity for an agent to actively control its environment. While conceptually appealing as an information-theoretic quantity, the connection between empowe…
Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents
Bartłomiej Cupiał, Jens Tuyls, Maciej Wołczyk +5
Language agents struggle to act and learn in environments that require long sequences of low-level actions. Code-based abstractions can make these agents more productive by letting…
Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning
Emmy Blumenthal, Nikolas Claussen, Benjamin Eysenbach +4
The last decade has seen the development of powerful methods for learning complex structure from high-dimensional data. These advances have brought to the foreground fundamental co…
Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL
Michal Korniak, Kamil Dybek, Benjamin Eysenbach +2
While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open question is the time scale ove…
LeAct: Learning to Reason from Expert Actions
Ziran Yang, Chengshuai Shi, Raj Ghugare +3
Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs. However, a rich and largely untapped source of supervision l…
Behavior-Consistent Deep Reinforcement Learning
Marcel Hussing, Liv G. d'Aliberti, Claas Voelcker +2
Reinforcement learning (RL) often exhibits high variance across training runs, leading to unreliable performance and posing a major challenge to deployment in real-world domains. I…
Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning
Aravind Venugopal, Jiayu Chen, Xudong Wu +3
The temporal lag between actions and their long-term consequences makes credit assignment a challenge when learning goal-directed behaviors from data. Generative world models captu…
Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards
Faisal Mohamed, Catherine Ji, Benjamin Eysenbach +1
Effective exploration in reinforcement learning requires not only tracking where an agent has been, but also understanding how the agent perceives and represents the world. To lear…
UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs
Devan Shah, Owen Yang, Daniel Yang +2
Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of large language models (LLMs) on mathematics and programming tasks, but standard approa…
Can We Really Learn One Representation to Optimize All Rewards?
Chongyi Zheng, Royina Karegoudra Jayanth, Benjamin Eysenbach
As unsupervised pretraining becomes increasingly ubiquitous in reinforcement learning, a more thorough theoretical understanding of these methods becomes of equal importance to the…
On the Role of Computation in Reinforcement Learning
Raj Ghugare, Michał Bortkiewicz, Alicja Ziarko +1
How does the amount of compute available to a reinforcement learning (RL) policy affect its learning? Can policies using a fixed amount of parameters, still benefit from additional…
SLAP: Shortcut Learning for Abstract Planning
Y. Isabel Liu, Bowen Li, Benjamin Eysenbach +1
Long-horizon decision-making with sparse rewards and continuous states and actions remains a fundamental challenge in AI and robotics. Task and motion planning (TAMP) is a model-ba…
Low-N Protein Activity Optimization with FolDE
Jacob B. Roberts, Catherine R. Ji, Isaac Donnell +13
Proteins are traditionally optimized through the costly construction and measurement of many mutants. Active Learning-assisted Directed Evolution (ALDE) alleviates that cost by pre…
Is Temporal Difference Learning the Gold Standard for Stitching in RL?
Michał Bortkiewicz, Władysław Pałucki, Mateusz Ostaszewski +1
Reinforcement learning (RL) promises to solve long-horizon tasks even when training data contains only short fragments of the behaviors. This experience stitching capability is oft…
Consistent Zero-Shot Imitation with Contrastive Goal Inference
Kathryn Wantlin, Chongyi Zheng, Benjamin Eysenbach
Zero-shot imitation learning requires an agent to reproduce expert behavior from a single demonstration without additional environment interaction or gradient updates at test time.…
Value Flows
Perry Dong, Chongyi Zheng, Chelsea Finn +2
While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods exploit the return distribution to pr…
BuilderBench: The Building Blocks of Intelligent Agents
Raj Ghugare, Roger Creus Castanyer, Catherine Ji +4
Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel…
Contrastive Representations for Temporal Reasoning
Alicja Ziarko, Michal Bortkiewicz, Michal Zawalski +2
In classical AI, perception relies on learning state-based representations, while planning, which can be thought of as temporal reasoning over action sequences, is typically achiev…
Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations
Vivek Myers, Bill Chunyuan Zheng, Benjamin Eysenbach +1
Approaches for goal-conditioned reinforcement learning (GCRL) often use learned state representations to extract goal-reaching policies. Two frameworks for representation structure…
Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
Chirayu Nimonkar, Shlok Shah, Catherine Ji +1
For groups of autonomous agents to achieve a particular goal, they must engage in coordination and long-horizon reasoning. Rather than relying on complex reward functions and expli…