Aimed at adapting a generative model to a novel generation task with only a few given data samples, the capability of few-shot generation is crucial for many realworld applications with limited data, e.g., artistic domains. Instead of training from scratch, recent works tend to leverage the prior knowledge stored in previous datasets, which is quite similar to the memory mechanism of human intelligence, but few of these works directly imitate the memory-recall mechanism that humans make good use of in accomplishing creative tasks, e.g., painting and writing. Inspired by the memory mechanism of human brain, in this work, we carefully design a variational structured memory module (VSM), which can simultaneously store both episodic and semantic memories to assist existing generative models efficiently recall these memories during sample generation. Meanwhile, we introduce a bionic memory updating strategy for the conversion between episodic and semantic memories, which can also model the uncertainty during conversion. Then, we combine the developed VSM with various generative models under the Bayesian framework, and evaluate these memory-augmented generative models with few-shot generation tasks, demonstrating the effectiveness of our methods.

Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the "induced" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local actionobservation histories, and can capture the interaction between agents due to reward backpropagation during centralized training. Therefore, we use prediction errors of individual Q-values as intrinsic rewards for coordinated exploration and utilize episodic memory to exploit explored informative experience to boost policy training. As the dynamics of an agent's individual Q-value function captures the novelty of states and the influence from other agents, our intrinsic reward can induce coordinated exploration to new or promising states. We illustrate the advantages of our method by didactic examples, and demonstrate its significant outperformance over state-of-the-art MARL baselines on challenging tasks in the StarCraft II micromanagement benchmark.

Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the "induced" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local actionobservation histories, and can capture the interaction between agents due to reward backpropagation during centralized training. Therefore, we use prediction errors of individual Q-values as intrinsic rewards for coordinated exploration and utilize episodic memory to exploit explored informative experience to boost policy training. As the dynamics of an agent's individual Q-value function captures the novelty of states and the influence from other agents, our intrinsic reward can induce coordinated exploration to new or promising states. We illustrate the advantages of our method by didactic examples, and demonstrate its significant outperformance over state-of-the-art MARL baselines on challenging tasks in the StarCraft II micromanagement benchmark.

Neural Information Processing Systems http://nips.cc/

Our proposed formulation for neuron calibration is lightweight and applicable to general feed-forward neural networks-based models.

To remove the limitation of short-term memory, Zhen et al.