4 papers
MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
Tristan Tomilin, Luka van den Boogaard, Samuel Garcin +7
Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning…
Beyond Pixel Histories: World Models with Persistent 3D State
Samuel Garcin, Thomas Walker, Steven McDonagh +5
Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D rep…
Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning
Samuel Garcin, Trevor McInroe, Pablo Samuel Castro +4
Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further co…
PixelBrax: Learning Continuous Control from Pixels End-to-End on the GPU
Trevor McInroe, Samuel Garcin
We present PixelBrax, a set of continuous control tasks with pixel observations. We combine the Brax physics engine with a pure JAX renderer, allowing reinforcement learning (RL) e…