• ☀️ By day at the University of Southampton, I explore how to understand and explain the decision making of reinforcement learning agent, in particular, the goals and future aims of an agent. This work is completed within the MINDS CDT with a sponsorship from the Royal Bank of Canada.
• 🌙 By night (and often during the day), I am the project manager ofGymnasium andGym, the de facto Reinforcement Learning environment APIs. This is as I am member of theFarama Foundation, you can read more about ithere

PinnedLoading

1. Farama-Foundation/GymnasiumFarama-Foundation/GymnasiumPublic

   An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

   Python 8.6k 958

2. temporal-reward-decompositiontemporal-reward-decompositionPublic

   Implementation of "Explaining an Agent’s Future Beliefs through Temporally Decomposing Future Reward Estimators"

   Python 3

3. temporal-explanations-4-drltemporal-explanations-4-drlPublic

   Implementation of "Temporal Explanations for Explainable Reinforcement Learning"

   Jupyter Notebook