Marcell Vazquez-Chanlatte

reinforcement learning (1) imitation learning (1) maximum entropy (1) transfer learning (1) hierarchical reinforcement learning (1) reward learning (1) learning from demonstration (1) zero-shot generalization (1) goal-conditioned reinforcement learning (1) goal-conditioned rl (1) automaton embedding (1) temporal logic (1) deterministic finite automaton (1) reward inference (1) goal-conditioned learning (1) task specification (1) graph neural network (1) finite automaton (1) boolean logic (1) specification inference (1)