Research

Work focused on hybrid RL architectures, reward design, and sample-efficient decision making. Pre-prints and code linked when available.

Hybrid Reinforcement Learning Agent

In Progress
Reinforcement LearningHybrid MethodsDecision Making

Developing a hybrid RL architecture that combines model-free and model-based approaches to improve sample efficiency and generalisation. The agent maintains a learned world model for planning while retaining a policy network for reactive behaviour in high-variance environments.

  • Combines Dreamer-style latent planning with SAC policy learning
  • Tested on continuous control benchmarks (MuJoCo, DMControl)
  • Reward shaping via learned auxiliary objectives

More work to be added. Pre-prints will link to arXiv when available.