Reinforcement learning, which spurs AI to complete goals using rewards or punishments, is a form of training that's led to gains in robotics, speech synthesis, and more. Unfortunately, it's data-intensive, which motivated research teams -- one from Google Brain (one of Google's AI research divisions) and the other from Alphabet's DeepMind -- to prototype more efficient means of executing it. In a pair of preprint papers, the researchers propose Adaptive Behavior Policy Sharing (ABPS), an algorithm that allows the sharing of experience adaptively selected from a pool of AI agents, and a framework -- Universal Value Function Approximators (UVFA) -- that simultaneously learns directed exploration policies with the same AI, with different trade-offs between exploration and exploitation. The teams claim ABPS achieves superior performance in several Atari games, reducing variance on top agents by 25%. As for UVFA, it doubles the performance of base agents in "hard exploration" in many of the same games while maintaining a high score across the remaining games; it's the first algorithm to achieve a high score in Pitfall without human demonstrations or hand-crafted features.

Most current reinforcement learning algorithms are not capable of effectively handling such a large number of possible actions per turn. Poor sample efficiency, consequently, results in agents that are unable to pass bottleneck states, where they are unable to proceed because they do not see the right action sequence to pass the bottleneck enough times to be sufficiently reinforced. Building on prior work using knowledge graphs in reinforcement learning, we introduce two new game state exploration strategies. We compare our exploration strategies against strong baselines on the classic text-adventure game, Zork1, where prior agent have been unable to get past a bottleneck where the agent is eaten by a Grue.

We develop a method for predicting the performance of reinforcement learning and bandit algorithms, given historical data that may have been generated by a different algorithm. Our estimator has the property that its prediction converges in probability to the true performance of a counterfactual algorithm at the fast $\sqrt{N}$ rate, as the sample size $N$ increases. We also show a correct way to estimate the variance of our prediction, thus allowing the analyst to quantify the uncertainty in the prediction. These properties hold even when the analyst does not know which among a large number of potentially important state variables are really important. These theoretical guarantees make our estimator safe to use. We finally apply it to improve advertisement design by a major advertisement company. We find that our method produces smaller mean squared errors than state-of-the-art methods.

The stringent requirements of mobile edge computing (MEC) applications and functions fathom the high capacity and dense deployment of MEC hosts to the upcoming wireless networks. However, operating such high capacity MEC hosts can significantly increase energy consumption. Thus, a BS unit can act as a self-powered BS. In this paper, an effective energy dispatch mechanism for self-powered wireless networks with edge computing capabilities is studied. First, a two-stage linear stochastic programming problem is formulated with the goal of minimizing the total energy consumption cost of the system while fulfilling the energy demand. Second, a semi-distributed data-driven solution is proposed by developing a novel multi-agent meta-reinforcement learning (MAMRL) framework to solve the formulated problem. In particular, each BS plays the role of a local agent that explores a Markovian behavior for both energy consumption and generation while each BS transfers time-varying features to a meta-agent. Sequentially, the meta-agent optimizes (i.e., exploits) the energy dispatch decision by accepting only the observations from each local agent with its own state information. Meanwhile, each BS agent estimates its own energy dispatch policy by applying the learned parameters from meta-agent. Finally, the proposed MAMRL framework is benchmarked by analyzing deterministic, asymmetric, and stochastic environments in terms of non-renewable energy usages, energy cost, and accuracy. Experimental results show that the proposed MAMRL model can reduce up to 11% non-renewable energy usage and by 22.4% the energy cost (with 95.8% prediction accuracy), compared to other baseline methods.

This paper revisits the celebrated temporal difference (TD) learning algorithm for the policy evaluation in reinforcement learning. Typically, the performance of the plain-vanilla TD algorithm is sensitive to the choice of stepsizes. Oftentimes, TD suffers from slow convergence. Motivated by the tight connection between the TD learning algorithm and the stochastic gradient methods, we develop the first adaptive variant of the TD learning algorithm with linear function approximation that we term AdaTD. In contrast to the original TD, AdaTD is robust or less sensitive to the choice of stepsizes. Analytically, we establish that to reach an $\epsilon$ accuracy, the number of iterations needed is $\tilde{O}(\epsilon^2\ln^4\frac{1}{\epsilon}/\ln^4\frac{1}{\rho})$, where $\rho$ represents the speed of the underlying Markov chain converges to the stationary distribution. This implies that the iteration complexity of AdaTD is no worse than that of TD in the worst case. Going beyond TD, we further develop an adaptive variant of TD($\lambda$), which is referred to as AdaTD($\lambda$). We evaluate the empirical performance of AdaTD and AdaTD($\lambda$) on several standard reinforcement learning tasks in OpenAI Gym on both linear and nonlinear function approximation, which demonstrate the effectiveness of our new approaches over existing ones.

In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincar\'e recurrence from normal-form games to zero-sum two-player imperfect information games and other sequential game settings. We then investigate how adapting the reward (by adding a regularization term) of the game can give strong convergence guarantees in monotone games. We continue by showing how this reward adaptation technique can be leveraged to build algorithms that converge exactly to the Nash equilibrium. Finally, we show how these insights can be directly used to build state-of-the-art model-free algorithms for zero-sum two-player Imperfect Information Games (IIG).

In this work we show how to use the Operational Space Control framework (OSC) under joint and cartesian constraints for reinforcement learning in cartesian space. Our method is therefore able to learn fast and with adjustable degrees of freedom, while we are able to transfer policies without additional dynamics randomizations on a KUKA LBR iiwa peg in-hole task. Before learning in simulation starts, we perform a system identification for aligning the simulation environment as far as possible with the dynamics of a real robot. Adding constraints to the OSC controller allows us to learn in a safe way on the real robot or to learn a flexible, goal conditioned policy that can be easily transferred from simulation to the real robot.

The recent advancements in cloud services, Internet of Things (IoT) and Cellular networks have made cloud computing an attractive option for intelligent traffic signal control (ITSC). Such a method significantly reduces the cost of cables, installation, number of devices used, and maintenance. ITSC systems based on cloud computing lower the cost of the ITSC systems and make it possible to scale the system by utilizing the existing powerful cloud platforms. While such systems have significant potential, one of the critical problems that should be addressed is the network delay. It is well known that network delay in message propagation is hard to prevent, which could potentially degrade the performance of the system or even create safety issues for vehicles at intersections. In this paper, we introduce a new traffic signal control algorithm based on reinforcement learning, which performs well even under severe network delay. The framework introduced in this paper can be helpful for all agent-based systems using remote computing resources where network delay could be a critical concern. Extensive simulation results obtained for different scenarios show the viability of the designed algorithm to cope with network delay.

Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity between tasks or select appropriate source policies to provide guided explorations for the target task. However, how to directly optimize the target policy by alternatively utilizing knowledge from appropriate source policies without explicitly measuring the similarity is currently missing. In this paper, we propose a novel Policy Transfer Framework (PTF) to accelerate RL by taking advantage of this idea. Our framework learns when and which source policy is the best to reuse for the target policy and when to terminate it by modeling multi-policy transfer as the option learning problem. PTF can be easily combined with existing deep RL approaches. Experimental results show it significantly accelerates the learning process and surpasses state-of-the-art policy transfer methods in terms of learning efficiency and final performance in both discrete and continuous action spaces.

Value estimation is a critical component of the reinforcement learning (RL) paradigm. The question of how to effectively learn predictors for value from data is one of the major problems studied by the RL community, and different approaches exploit structure in the problem domain in different ways. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. In contrast, model-free methods directly leverage the quantity of interest from the future but have to compose with a potentially weak scalar signal (an estimate of the return). In this paper we develop an approach for representation learning in RL that sits in between these two extremes: we propose to learn what to model in a way that can directly help value prediction. To this end we determine which features of the future trajectory provide useful information to predict the associated return. This provides us with tractable prediction targets that are directly relevant for a task, and can thus accelerate learning of the value function. The idea can be understood as reasoning, in hindsight, about which aspects of the future observations could help past value prediction. We show how this can help dramatically even in simple policy evaluation settings. We then test our approach at scale in challenging domains, including on 57 Atari 2600 games.