Maximizing Information Gain in Partially Observable Environments via Prediction Rewards

Information gathering in a partially observable environment can be formulated as a reinforcement learning (RL), problem where the reward depends on the agent's uncertainty. For example, the reward can be the negative entropy of the agent's belief over an unknown (or hidden) variable. Typically, the rewards of an RL agent are defined as a...

Plannable Approximations to MDP Homomorphisms: Equivariance under Actions

This work exploits action equivariance for representation learning in reinforcement learning. Equivariance under actions states that transitions in the input space are mirrored by equivalent transitions in latent space, while the map and transition functions should also commute. We introduce a contrastive loss function that enforces action...

Generalized Optimistic Q-Learning with Provable Efficiency

Reinforcement learning (RL), like any on-line learning method, inevitably faces the exploration-exploitation dilemma. When a learning algorithm requires as few data samples as possible, it is called sample efficient. The design of sample-efficient algorithms is an important area of research. Interestingly, all currently known provably efficient...

Elessar: Ethics in Norm-Aware Agents

We address the problem of designing agents that navigate social norms by selecting ethically appropriate actions. We present Elessar, a framework in which agents aggregate value preferences of users and select ethically appropriate actions through multicriteria decision making in different social contexts. Via simulations, seeded with a survey...

New foundations of ethical multiagent systems blue sky ideas track

Ethics is inherently a multiagent concern. However, research on AI ethics today is dominated by work on individual agents: (1) how an autonomous robot or car may harm or (differentially) benefit people in hypothetical situations (the so-called trolley problems) and (2) how a machine learning algorithm may produce biased decisions or...

Automated configuration of negotiation strategies

Bidding and acceptance strategies have a substantial impact on the outcome of negotiations in scenarios with linear additive and nonlinear utility functions. Over the years, it has become clear that there is no single best strategy for all negotiation settings, yet many fixed strategies are still being developed. We envision a shift in the...

The Power of Social Features in Online Gaming

Within the vast and rich field of online gaming, a new generation of Online Social Games (OSGs) is emerging that have in common a core of social interaction, sometimes explicit, other times implicit. This common core of social experience promises to become at least as important as the experience derived from the game-­‐world itself. In this...