13 citations · 25 across the 13 of their papers we have counts for
9 papers · 1 filter
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
Alexander Rutherford, Michael Beukman, Timon Willi +3
What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised E…
Mixture of Experts in a Mixture of RL settings
Timon Willi, Johan Obando-Ceron, Jakob Foerster +2
Mixtures of Experts (MoEs) have gained prominence in (self-)supervised learning due to their enhanced inference efficiency, adaptability to distributed training, and modularity. Pr…
Analysing the Sample Complexity of Opponent Shaping
Kitty Fung, Qizhen Zhang, Chris Lu +3
Learning in general-sum games often yields collectively sub-optimal results. Addressing this, opponent shaping (OS) methods actively guide the learning processes of other agents, e…
Mixtures of Experts Unlock Parameter Scaling for Deep RL
Johan Obando-Ceron, Ghada Sokar, Timon Willi +6
The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance scales proportionally to its size. Analog…
Leading the Pack: N-player Opponent Shaping
Alexandra Souly, Timon Willi, Akbir Khan +4
Reinforcement learning solutions have great success in the 2-player general sum setting. In this setting, the paradigm of Opponent Shaping (OS), in which agents account for the lea…
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
Alexander Rutherford, Benjamin Ellis, Matteo Gallici +18
Benchmarks are crucial in the development of machine learning algorithms, with available environments significantly influencing reinforcement learning (RL) research. Traditionally,…
Adversarial Cheap Talk
Chris Lu, Timon Willi, Alistair Letcher +1
Adversarial attacks in reinforcement learning (RL) often assume highly-privileged access to the victim's parameters, environment, or data. Instead, this paper proposes a novel adve…
COLA: Consistent Learning with Opponent-Learning Awareness
Timon Willi, Alistair Letcher, Johannes Treutlein +1
Learning in general-sum games is unstable and frequently leads to socially undesirable (Pareto-dominated) outcomes. To mitigate this, Learning with Opponent-Learning Awareness (LOL…
Recurrent Neural Processes
Timon Willi, Jonathan Masci, Jürgen Schmidhuber +1
We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Giv…