Lucas Caccia

Building a Subspace of Policies for Scalable Continual Learning

2022 · arXiv (Cornell University)

The ability to continuously acquire new knowledge and skills is crucial for autonomous agents. Existing methods are typically based on either fixed-size models that struggle to learn a large number of diverse behaviors, or growing-size …

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

2022 · arXiv (Cornell University)

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new …

Language GANs Falling Short

2020 · International Conference on Learning Representations

Traditional natural language generation (NLG) models are trained using maximum likelihood estimation (MLE) which differs from the sample generation inference procedure. During training the ground truth tokens are passed to the model, however, during inference, …