Sanjit Seshia

reward learning (2) reinforcement learning (1) imitation learning (1) maximum entropy (1) preference learning (1) inverse reinforcement learning (1) label ranking (1) learning from demonstration (1) stochastic game (1) multi-agent coordination (1) controller synthesis (1) reward inference (1) human-agent interaction (1) adversarial game (1) control synthesis (1) task specification (1) population-based training (1) reactive control (1) human-ai coordination (1) multi-agent system (1)