MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning

Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single reward model, thus rendering it difficult to trade off different reward functions from multiple experts. We...

Environment Shift Games: Are Multiple Agents the Solution, and not the Problem, to Non-Stationarity?

Machine learning and artificial intelligence models that interact with and in an environment will unavoidably have impact on this environment and change it. This is often a problem as many methods do not anticipate such a change in the environment and thus may start acting sub-optimally. Although efforts are made to deal with this problem, we...

Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which...

The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. In this work, we empirically investigate the representational power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial...