Mikayel Samvelyan

multi-agent reinforcement learning (6) centralized training (2) cooperative multi-agent (2) environment design (2) value function factorization (2) decentralized policy (2) adversarial learning (2) curriculum learning (1) offline reinforcement learning (1) sample efficiency (1) procedural generation (1) tensor decomposition (1) low-rank approximation (1) bellman equation (1) model safety (1) adversarial attack (1) adversarial training (1) temporal abstraction (1) partial observability (1) text generation (1)