49 citations · 92 across the 9 of their papers we have counts for
11 papers
Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning
Anthony GX-Chen, Ankit Anand, Gheorghe Comanici +7
Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fin…
Affordances Enable Partial World Modeling with LLMs
Khimya Khetarpal, Gheorghe Comanici, Jonathan Richens +5
Full models of the world require complex knowledge of immense detail. While pre-trained large models have been hypothesized to contain similar knowledge due to extensive pre-traini…
An AI system to help scientists write expert-level empirical software
Eser Aygün, Anastasiya Belyaeva, Gheorghe Comanici +39
The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments\cite{hannay2009how}. To address this, we…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Vision-Language Models as a Source of Rewards
Kate Baumli, Satinder Baveja, Feryal Behbahani +24
Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning. A key limiting factor for bui…
Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
Abbas Mehrabian, Ankit Anand, Hyunjik Kim +16
This work studies a central extremal graph theory problem inspired by a 1975 conjecture of Erdős, which aims to find graphs with a given size (number of nodes) that maximize the nu…
Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning
Gheorghe Comanici, Amelia Glaese, Anita Gergely +5
Hierarchical Reinforcement Learning (HRL) allows interactive agents to decompose complex problems into a hierarchy of sub-tasks. Higher-level tasks can invoke the solutions of lowe…
Temporally Abstract Partial Models
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici +1
Humans and animals have the ability to reason and make predictions about different courses of action at many time scales. In reinforcement learning, option models (Sutton, Precup \…
The Option Keyboard: Combining Skills in Reinforcement Learning
André Barreto, Diana Borsa, Shaobo Hou +8
The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended periods. We argue that a…
AndroidEnv: A Reinforcement Learning Platform for Android
Daniel Toyama, Philippe Hamel, Anita Gergely +6
We introduce AndroidEnv, an open-source platform for Reinforcement Learning (RL) research built on top of the Android ecosystem. AndroidEnv allows RL agents to interact with a wide…
What can I do here? A Theory of Affordances in Reinforcement Learning
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici +2
Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the feature…