Reinforcement Learning

M-SAT: Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Actions
Effective decision-making in complex environments with multi-discrete action spaces poses significant challenges for agent …
Cite
Using NEAT to Learn Operators for Flexible Boolean Composition within Reinforcement Learning
Skill composition is a growing area of interest within Reinforcement Learning (RL) research. For example, if designing a robot for …
PDF Cite Project
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 …
PDF Cite Project DOI
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 …
PDF Cite Project
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 …
PDF Cite Project
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 …
PDF Cite
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 …
Cite Project
Transferable Dynamics Models for Efficient Object-Oriented Reinforcement Learning
The Reinforcement Learning (RL) framework offers a general paradigm for constructing autonomous agents that can make effective …
PDF Cite DOI
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 …
PDF Cite Project
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 …
PDF Cite