Reinforcement Learning

Composition and Zero-Shot Transfer with Lattice Structures in Reinforcement Learning

An important property of long-lived agents is the ability to reuse existing knowledge to solve new tasks. An appealing approach towards …

Geraud Nangue Tasse, Steven James, Benjamin Rosman

Compositional Instruction Following with Language Models and Reinforcement Learning

Combining reinforcement learning with language grounding is challenging as the agent needs to explore the environment while …

Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew Gombolay, Ray Mooney, Benjamin Rosman

Optimal Task Generalisation in Cooperative Multi-Agent Reinforcement Learning

While task generalisation is widely studied in the context of single-agent reinforcement learning (RL), little research exists in the …

Simon Rosen, Abdel Mfougouon Njupoun, Geraud Nangue Tasse, Steven James, Benjamin Rosman

ROSARL: Reward-Only Safe Reinforcement Learning

An important problem in reinforcement learning is designing agents that learn to solve tasks safely in an environment. A common …

Geraud Nangue Tasse, Tamlin Love, Mark Nemecek, Steven James, Benjamin Rosman

Is There Safety in (Large Negative) Numbers?

A talk on reward design and safety in reinforcement learning, given at the “I Can’t Believe It’s Not Better” workshop at the Reinforcement Learning Conference.

1 Aug 2024 UMass Amherst

Concurrent and Temporal Composition for Zero-Shot Transfer in Reinforcement Learning

A talk on composing skills concurrently and over time to transfer to unseen tasks without further training.

10 Jul 2024 University of the Witwatersrand

Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning

It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same …

Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman

Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure

We present counting reward automata—a finite state machine variant capable of modelling any reward function expressible as a …

Tristan Bester, Benjamin Rosman, Steven James, Geraud Nangue Tasse

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies

While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many …

Michael Beukman, Devon Jarvis, Richard Klein, Steven James, Benjamin Rosman

Multitask Learning with Composition

A talk on composing learned skills to solve multiple tasks without retraining.

1 Oct 2023 ETH Zürich