3 citations · 5 across the 6 of their papers we have counts for
7 papers
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…
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…
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…
Normalizing Flows are Capable Models for Continuous Control
Raj Ghugare, Benjamin Eysenbach
Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models.…
Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View
Raj Ghugare, Matthieu Geist, Glen Berseth +1
Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-sought property is one of the few ways in wh…
Searching for High-Value Molecules Using Reinforcement Learning and Transformers
Raj Ghugare, Santiago Miret, Adriana Hugessen +2
Reinforcement learning (RL) over text representations can be effective for finding high-value policies that can search over graphs. However, RL requires careful structuring of the…
Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective
Raj Ghugare, Homanga Bharadhwaj, Benjamin Eysenbach +2
While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learnin…