A central challenge in multi-agent reinforcement learning is the induction of coordination between agents of a team. In this work, we investigate how to promote inter-agent coordination and discuss two possible avenues based respectively on inter-agent modelling and guided synchronized sub-policies. We test each approach in four challenging continuous control tasks with sparse rewards and compare them against three variants of MADDPG, a state-of-the-art multi-agent reinforcement learning algorithm. To ensure a fair comparison, we rely on a thorough hyper-parameter selection and training methodology that allows a fixed hyper-parameter search budget for each algorithm and environment. We consequently assess both the hyper-parameter sensitivity, sample-efficiency and asymptotic performance of each learning method. Our experiments show that our proposed algorithms are more robust to the hyper-parameter choice and reliably lead to strong results.

Computational challenges are further compounded if agents do not possess complete model knowledge. In this paper, we take advantage of the fact that in many problems agents share some common information, or history, termed partial history sharing . Under this information structure the policy search space is greatly reduced. We propose a provably convergent, online tree-search based algorithm that does not require a closed-form model or explicit communication among agents. Interestingly, our algorithm can be viewed as a generalization of several existing heuristic solvers for decentralized partially observable Markov decision processes. T o demonstrate the applicability of the model, we propose a novel collaborative intrusion response model, where multiple agents (defenders) possessing asymmetric information aim to collaboratively defend a computer network. Numerical results demonstrate the performance of our algorithm.

Evaluating novel contextual bandit policies using logged data is crucial in applications where exploration is costly, such as medicine. But it usually relies on the assumption of no unobserved confounders, which is bound to fail in practice. We study the question of policy evaluation when we instead have proxies for the latent confounders and develop an importance weighting method that avoids fitting a latent outcome regression model. We show that unlike the unconfounded case no single set of weights can give unbiased evaluation for all outcome models, yet we propose a new algorithm that can still provably guarantee consistency by instead minimizing an adversarial balance objective. We further develop tractable algorithms for optimizing this objective and demonstrate empirically the power of our method when confounders are latent.

Corrigibility is a safety property for artificially intelligent agents. A corrigible agent will not resist attempts by authorized parties to alter the goals and constraints that were encoded in the agent when it was first started. This paper shows how to construct a safety layer that adds corrigibility to arbitrarily advanced utility maximizing agents, including possible future agents with Artificial General Intelligence (AGI). The layer counter-acts the emergent incentive of advanced agents to resist such alteration. A detailed model for agents which can reason about preserving their utility function is developed, and used to prove that the corrigibility layer works as intended in a large set of non-hostile universes. The corrigible agents have an emergent incentive to protect key elements of their corrigibility layer. However, hostile universes may contain forces strong enough to break safety features. Some open problems related to graceful degradation when an agent is successfully attacked are identified. The results in this paper were obtained by concurrently developing an AGI agent simulator, an agent model, and proofs. The simulator is available under an open source license. The paper contains simulation results which illustrate the safety related properties of corrigible AGI agents in detail.

The EmbodiedQA is a task of training an embodied agent by intelligently navigating in a simulated environment and gathering visual information to answer questions. Existing approaches fail to explicitly model the mental imagery function of the agent, while the mental imagery is crucial to embodied cognition, and has a close relation to many high-level meta-skills such as generalization and interpretation. In this paper, we propose a novel Mental Imagery eNhanceD (MIND) module for the embodied agent, as well as a relevant deep reinforcement framework for training. The MIND module can not only model the dynamics of the environment (e.g. 'what might happen if the agent passes through a door') but also help the agent to create a better understanding of the environment (e.g. 'The refrigerator is usually in the kitchen'). Such knowledge makes the agent a faster and better learner in locating a feasible policy with only a few trails. Furthermore, the MIND module can generate mental images that are treated as short-term subgoals by our proposed deep reinforcement framework. These mental images facilitate policy learning since short-term subgoals are easy to achieve and reusable. This yields better planning efficiency than other algorithms that learn a policy directly from primitive actions. Finally, the mental images visualize the agent's intentions in a way that human can understand, and this endows our agent's actions with more interpretability. The experimental results and further analysis prove that the agent with the MIND module is superior to its counterparts not only in EQA performance but in many other aspects such as route planning, behavioral interpretation, and the ability to generalize from a few examples.

Rising Need for Better Product Management 4.2 Challenges 4.2.1 Slow Adoption Rate 4.2.2

This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then extended to a multi-agent variant of the proximal policy optimization algorithm and demonstrated on simple particle environments that have elements of system health, risk-taking, semi-expendable agents, and partial observability. We show significant improvement in learning performance compared to policy gradient methods that do not perform multi-agent credit assignment.

We consider the framework of learning over decentralized networks, where nodes observe unique, possibly correlated, observation streams. We focus on the case where agents learn a regression \emph{function} that belongs to a reproducing kernel Hilbert space (RKHS). In this setting, a decentralized network aims to learn nonlinear statistical models that are optimal in terms of a global stochastic convex functional that aggregates data across the network, with only access to a local data stream. We incentivize coordination while respecting network heterogeneity through the introduction of nonlinear proximity constraints. To solve it, we propose applying a functional variant of stochastic primal-dual (Arrow-Hurwicz) method which yields a decentralized algorithm. To handle the fact that the RKHS parameterization has complexity proportionate with the iteration index, we project the primal iterates onto Hilbert subspaces that are greedily constructed from the observation sequence of each node. The resulting proximal stochastic variant of Arrow-Hurwicz, dubbed Heterogeneous Adaptive Learning with Kernels (HALK), is shown to converge in expectation, both in terms of primal sub-optimality and constraint violation to a neighborhood that depends on a given constant step-size selection. Simulations on a correlated spatio-temporal random field estimation problem validate our theoretical results, which are born out in practice for networked oceanic sensing buoys estimating temperature and salinity from depth measurements.

We show how norms can be used to guide a reinforcement learning agent towards achieving normative behavior and apply the same set of norms over different domains. Thus, we are able to: (1) provide a way to intuitively encode social knowledge (through norms); (2) guide learning towards normative behaviors (through an automatic norm reward system); and (3) achieve a transfer of learning by abstracting policies; Finally, (4) the method is not dependent on a particular RL algorithm. We show how our approach can be seen as a means to achieve abstract representation and learn procedural knowledge based on the declarative semantics of norms and discuss possible implications of this in some areas of cognitive science. Index T erms --Norms, Institutions, Automatic Reward Shaping, Transfer of Learning, Abstract Policies, Abstraction, State-Space Selection, Schema I. I NTRODUCTION In order to be accepted in human society, robots need to comply with human social norms.

Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement learning provides a framework to automatically acquire suitable reward functions from expert demonstrations. Its extension to multi-agent settings, however, is difficult due to the more complex notions of rational behaviors. In this paper, we propose MA-AIRL, a new framework for multi-agent inverse reinforcement learning, which is effective and scalable for Markov games with high-dimensional state-action space and unknown dynamics. We derive our algorithm based on a new solution concept and maximum pseudolikelihood estimation within an adversarial reward learning framework. In the experiments, we demonstrate that MA-AIRL can recover reward functions that are highly correlated with ground truth ones, and significantly outperforms prior methods in terms of policy imitation.