Bei Peng

multi-agent reinforcement learning (4) commonsense generation (2) value function (2) reinforcement learning (2) interactive learning (1) transfer learning (1) image classification (1) cooperative multi-agent (1) natural language generation (1) text generation (1) multimodal learning (1) policy learning (1) deepfake detection (1) evaluation methodology (1) generative model (1) in-context learning (1) human feedback (1) counterfactual reasoning (1) curriculum learning (1) multi-task learning (1)