Sunil Mallya

multi-agent reinforcement learning (1) contrastive learning (1) reinforcement learning (1) few-shot learning (1) policy gradient (1) knowledge transfer (1) named entity recognition (1) semantic matching (1) model uncertainty (1) nash equilibrium (1) document classification (1) semantic information (1) zero-shot classification (1) semi-structured document (1) label semantics (1) representation transfer (1) teacher policy (1) advantage-based selection (1) layout information (1) robust markov game (1)