papers

Publications (7)

cs.LG2022

Reinforcement Learning in Presence of Discrete Markovian Context Evolution

Hang Ren, Aivar Sootla, Taher Jafferjee +3

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (disconti…

cs.LG2022

Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation

Aivar Sootla, Alexander I. Cowen-Rivers, Taher Jafferjee +4

Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications. For example, plan…

cs.LG2026

Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models

Farzane Aminmansour, Taher Jafferjee, Ehsan Imani +3

Dyna-style reinforcement learning (RL) agents improve sample efficiency over model-free RL agents by updating the value function with simulated experience generated by an environme…

cs.LG2023

Learning to Shape Rewards using a Game of Two Partners

David Mguni, Taher Jafferjee, Jianhong Wang +9

Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engi…

cs.MA2022

LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning

David Henry Mguni, Taher Jafferjee, Jianhong Wang +7

Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to joint…

cs.MA2023

Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction

Taher Jafferjee, Juliusz Ziomek, Tianpei Yang +6

Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. Despite its popularity, it…