Carbon‐supported metal nanoparticles (NPs) play important roles in heterogeneous catalysis. In particular, supported bimetallic catalytic systems can be promising multifunctional catalysts for one‐pot tandem/cascade reactions, in which two or more successive independent reactions are realized in one pot. In this manuscript, we report the preparation of a carbon‐supported bimetallic CoCu catalytic system (Co−C@Cu−C), with Co NPs wrapped by carbon‐supported Cu NPs, from the pyrolysis of a core‐shell structured Co−MOF‐74@Cu−MOF‐74. The as‐obtained Co−C@Cu−C acts as a bifunctional catalyst for the transformation of phenylacetylene to 1, 4‐diphenyl‐1, 3‐butadiene in one pot, in which supported metallic Cu NPs and Co NPs are active for the coupling and hydrogenation reaction respectively. By tuning the reaction rates of the coupling and the hydrogenation in this tandem reaction over the Co−C@Cu−C via changing the reaction medium and the reducing agent, an efficient direct transformation of phenylacetylene to 1, 4‐diphenyl‐1, 3‐butadiene was realized. This work not only highlights the important role of MOFs in the preparation of multifunctional carbon supported metal NPs for heterogeneous catalysis, but also demonstrates the possibility of tuning the reaction rates of different catalytic steps in a tandem reaction to realize an efficient overall reaction.

Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning. However, the requirement of isolated single modal demonstrations limits the scalability of the approach to real world scenarios such as autonomous vehicles' demand for a proper understanding of human drivers' behavior. In this paper, we propose a novel multi-modal GAIL framework, named Triple-GAIL, that is able to learn skill selection and imitation jointly from both expert demonstrations and continuously generated experiences with data augmentation purpose by introducing an auxiliary selector. We provide theoretical guarantees on the convergence to optima for both of the generator and the selector respectively. Experiments on real driver trajectories and real-time strategy game datasets demonstrate that Triple-GAIL can better fit multi-modal behaviors close to the demonstrators and outperforms state-of-the-art methods.

Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning. However, the requirement of isolated single modal demonstrations limits the scalability of the approach to real world scenarios such as autonomous vehicles' demand for a proper understanding of human drivers' behavior. In this paper, we propose a novel multi-modal GAIL framework, named Triple-GAIL, that is able to learn skill selection and imitation jointly from both expert demonstrations and continuously generated experiences with data augmentation purpose by introducing an auxiliary skill selector. We provide theoretical guarantees on the convergence to optima for both of the generator and the selector respectively. Experiments on real driver trajectories and realtime strategy game datasets demonstrate that Triple-GAIL can better fit multi-modal behaviors close to the demonstrators and outperforms state-of-the-art methods.

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures. In this paper, we cast the multiagent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents' policies, which can recover agents' policies that can regenerate similar interactions. Consequently, we develop a Decentralized Adversarial Imitation Learning algorithm with Correlated policies (CoDAIL), which allows for decentralized training and execution. Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators and outperforms state-of-the-art multi-agent imitation learning methods. Our code is available at https://github.com/apexrl/CoDAIL.

No abstract