We consider the networked multi-agent reinforcement learning (MARL) problem in a fully decentralized setting, where agents learn to coordinate to achieve joint success. This problem is widely encountered in many areas including traffic control, distributed control, and smart grids. We assume each agent is located at a node of a communication network and can exchange information only with its neighbors. Using softmax temporal consistency, we derive a primal-dual decentralized optimization method and obtain a principled and data-efficient iterative algorithm named {\em value propagation}. We prove a non-asymptotic convergence rate of $\mathcal{O}(1/T)$ with nonlinear function approximation.

Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the λ-return difficult in this context. In particular, off-policy methods that utilize experience replay remain problematic because their random sampling of minibatches is not conducive to the efficient calculation of λ-returns. Yet replay-based methods are often the most sample efficient, and incorporating λ-returns into them is a viable way to achieve new state-of-the-art performance. Towards this, we propose the first method to enable practical use of λ-returns in arbitrary replay-based methods without relying on other forms of decorrelation such as asynchronous gradient updates. By promoting short sequences of past transitions into a small cache within the replay memory, adjacent λ-returns can be efficiently precomputed by sharing Q-values.

We consider an agent who is involved in an online Markov decision process, and receives a vector of outcomes every round. The agent aims to simultaneously optimize multiple objectives associated with the multi-dimensional outcomes. Due to state transitions, it is challenging to balance the vectorial outcomes for achieving near-optimality. In particular, contrary to the single objective case, stationary policies are generally sub-optimal. We propose a no-regret algorithm based on the Frank-Wolfe algorithm (Frank and Wolfe 1956), UCRL2 (Jaksch et al. 2010), as well as a crucial and novel gradient threshold procedure.

Proximal policy optimization (PPO) is one of the most popular deep reinforcement learning (RL) methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, as a model-free RL method, the success of PPO relies heavily on the effectiveness of its exploratory policy search. In this paper, we give an in-depth analysis on the exploration behavior of PPO, and show that PPO is prone to suffer from the risk of lack of exploration especially under the case of bad initialization, which may lead to the failure of training or being trapped in bad local optima. To address these issues, we proposed a novel policy optimization method, named Trust Region-Guided PPO (TRGPPO), which adaptively adjusts the clipping range within the trust region. We formally show that this method not only improves the exploration ability within the trust region but enjoys a better performance bound compared to the original PPO as well.

From traditional Web search engines to virtual assistants and Web accelerators, services that rely on online information need to continually keep track of remote content changes by explicitly requesting content updates from remote sources (e.g., web pages). We propose a novel optimization objective for this setting that has several practically desirable properties, and efficient algorithms for it with optimality guarantees even in the face of mixed content change observability and initially unknown change model parameters. Experiments on 18.5M URLs crawled daily for 14 weeks show significant advantages of this approach over prior art. Papers published at the Neural Information Processing Systems Conference.

Interacting with a complex world involves continual learning, in which tasks and data distributions change over time. A continual learning system should demonstrate both plasticity (acquisition of new knowledge) and stability (preservation of old knowledge). Catastrophic forgetting is the failure of stability, in which new experience overwrites previous experience. In the brain, replay of past experience is widely believed to reduce forgetting, yet it has been largely overlooked as a solution to forgetting in deep reinforcement learning. Here, we introduce CLEAR, a replay-based method that greatly reduces catastrophic forgetting in multi-task reinforcement learning.

Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those frameworks demonstrate appealing performance on a variety of domains such as few-shot image classification and reinforcement learning. However, one important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiting the diversity of the task distributions that they are able to learn from. In this paper, we augment MAML with the capability to identify the mode of tasks sampled from a multimodal task distribution and adapt quickly through gradient updates. Specifically, we propose a multimodal MAML (MMAML) framework, which is able to modulate its meta-learned prior parameters according to the identified mode, allowing more efficient fast adaptation. We evaluate the proposed model on a diverse set of few-shot learning tasks, including regression, image classification, and reinforcement learning.

Our aim is to establish a framework where reinforcement learning (RL) of optimizing interventions retrospectively allows us a regulatory compliant pathway to prospective clinical testing of the learned policies in a clinical deployment. We focus on infections in intensive care units which are one of the major causes of death and difficult to treat because of the complex and opaque patient dynamics, and the clinically debated, highly-divergent set of intervention policies required by each individual patient, yet intensive care units are naturally data rich. In our work, we build on RL approaches in healthcare ("AI Clinicians"), and learn off-policy continuous dosing policy of pharmaceuticals for sepsis treatment using historical intensive care data under partially observable MDPs (POMDPs). POMPDs capture uncertainty in patient state better by taking in all historical information, yielding an efficient representation, which we investigate through ablations. We compensate for the lack of exploration in our retrospective data by evaluating each encountered state with a best-first tree search. We mitigate state distributional shift by optimizing our policy in the vicinity of the clinicians' compound policy. Crucially, we evaluate our model recommendations using not only conventional policy evaluations but a novel framework that incorporates human experts: a model-agnostic pre-clinical evaluation method to estimate the accuracy and uncertainty of clinician's decisions versus our system recommendations when confronted with the same individual patient history ("shadow mode").

Routing is one of the key functions for stable operation of network infrastructure. Nowadays, the rapid growth of network traffic volume and changing of service requirements call for more intelligent routing methods than before. Towards this end, we propose a definition of cognitive routing and an implementation approach based on Deep Reinforcement Learning (DRL). To facilitate the research of DRL-based cognitive routing, we introduce a simulator named RL4Net for DRL-based routing algorithm development and simulation. Then, we design and implement a DDPG-based routing algorithm. The simulation results on an example network topology show that the DDPG-based routing algorithm achieves better performance than OSPF and random weight algorithms. It demonstrate the preliminary feasibility and potential advantage of cognitive routing for future network.

The solution of many continuous decision problem can be described as such a process: agent set out from the initial state, then go through a series of intermediate state and finally reach the goal state. Imagine an agent in a maze, which needs to find some key positions and pass through them one by one to get out. Agent has two types of behavior: one is the micro action taken at every state, which is similar to muscle activity, called reaction; another is the change of trend in reactions taken over a period of time, which is similar to thought of human, called planning [15]. For the agent in maze, reaction can be its every little moving step and planning can be its every determination of the position it should reach next. In a complicated scene with high-dimensional data stream, long-term decision process and sparse supervision signal, an agent trained only to react [9, 10] can hardly perform well (See Appendix A for demonstration). However, combining reaction and planning [3, 4, 14] can significantly improve its capability. The essence of such improvement is that agent has limited reaction capability and the introduction of planning releases agent from reacting in the whole task.