Filippos Christianos

multi-agent system (2) multi-agent reinforcement learning (2) deep reinforcement learning (2) policy optimization (1) policy learning (1) parameter sharing (1) partial observability (1) sparse reward (1) encoder-decoder architecture (1) ad hoc teamwork (1) experience sharing (1) graph neural network (1) neural network (1) agent partitioning (1) agent modelling (1) reinforcement learning (1) sample efficiency (1)