Nikola Momchev

reward function (2) imitation learning (2) sequence modeling (1) reinforcement learning (1) semantic parsing (1) policy learning (1) natural language understanding (1) inverse reinforcement learning (1) compositional generalization (1) reinforcement learning from human feedback (1) continuous control (1) hyperparameter tuning (1) language model (1) expert demonstration (1) transformer neural network (1) textual entailment (1) reference-free evaluation (1) language model fine-tuning (1) scalability analysis (1) abstractive summarization (1)