81 citations
- Google (United States)US4 papers
- Centre Universitaire de MilaDZ2 papers
- Columbia UniversityUS2 papers
- Google DeepMind (United Kingdom)GB2 papers
- Kao Corporation (Japan)JP2 papers
- Université de MontréalCA2 papers
- Berlin Institute for the Foundations of Learning and DataDE1 paper
- Bernstein Center for Computational Neuroscience FreiburgDE1 paper
- Center for Pain and the BrainUS1 paper
- Center for Visual Communication (United States)US1 paper
- Douglas Mental Health University InstituteCA1 paper
- Duke UniversityUS1 paper
4 papers · 1 filter
Hyperparameter Selection for Imitation Learning
Leonard Hussenot, Marcin Andrychowicz, Damien Vincent +11
We address the issue of tuning hyperparameters (HPs) for imitation learning algorithms in the context of continuous-control, when the underlying reward function of the demonstratin…
Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
Rishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro +1
Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generalization, we incorporate the inherent sequ…
Revisiting Fundamentals of Experience Replay
William Fedus, Prajit Ramachandran, Rishabh Agarwal +4
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic…
Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data
Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo +1
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However,…