Pierre-Luc Bacon

reinforcement learning (5) continuous control (2) policy optimization (2) policy gradient (2) sample efficiency (1) off-policy evaluation (1) sequence modeling (1) importance sampling (1) maximum entropy (1) markov decision process (1) function approximation (1) attention mechanism (1) constrained reinforcement learning (1) language modeling (1) hierarchical reinforcement learning (1) markov chain monte carlo (1) imitation learning (1) maximum likelihood (1) contrastive learning (1) transformer architecture (1)