We provide the first solution for model-free reinforcement learning of {\omega}-regular objectives for Markov decision processes (MDPs). We present a constructive reduction from the almost-sure satisfaction of {\omega}-regular objectives to an almost- sure reachability problem and extend this technique to learning how to control an unknown model so that the chance of satisfying the objective is maximized. A key feature of our technique is the compilation of {\omega}-regular properties into limit- deterministic Buechi automata instead of the traditional Rabin automata; this choice sidesteps difficulties that have marred previous proposals. Our approach allows us to apply model-free, off-the-shelf reinforcement learning algorithms to compute optimal strategies from the observations of the MDP. We present an experimental evaluation of our technique on benchmark learning problems.

A longstanding goal of behavior-based robotics is to solve high-level navigation tasks using end to end navigation behaviors that directly map sensors to actions. Navigation behaviors, such as reaching a goal or following a path without collisions, can be learned from exploration and interaction with the environment, but are constrained by the type and quality of a robot's sensors, dynamics, and actuators. Traditional motion planning handles varied robot geometry and dynamics, but typically assumes high-quality observations. Modern vision-based navigation typically considers imperfect or partial observations, but simplifies the robot action space. With both approaches, the transition from simulation to reality can be difficult. Here, we learn two end to end navigation behaviors that avoid moving obstacles: point to point and path following. These policies receive noisy lidar observations and output robot linear and angular velocities. We train these policies in small, static environments with Shaped-DDPG, an adaptation of the Deep Deterministic Policy Gradient (DDPG) reinforcement learning method which optimizes reward and network architecture. Over 500 meters of on-robot experiments show , these policies generalize to new environments and moving obstacles, are robust to sensor, actuator, and localization noise, and can serve as robust building blocks for larger navigation tasks. The path following and point and point policies are 83% and 56% more successful than the baseline, respectively.

Open relation extraction (ORE) remains a challenge to obtain a semantic representation by discovering arbitrary relation tuples from the un-structured text. However, perhaps due to limited data, previous extractors use unsupervised or semi-supervised methods based on pattern matching, which heavily depend on manual work or syntactic parsers and are inefficient or error-cascading. Their development has encountered bottlenecks. Although a few people try to use neural network based models to improve the ORE task performance recently, it is always intractable for ORE to produce supervised systems based on various neural architectures. We analyze and review the neural ORE methods. Further, we construct a large-scale automatically tagging training set and design a tagging scheme to frame ORE as a supervised sequence tagging task. A hybrid neural sequence tagging model (NST) is proposed which combines BiLSTM, CNN and CRF to capture the contextual temporal information, local spatial information, and sentence level tag information of the sequence by using the word and part-of-speech embeddings. Experiments on multiple datasets show that our method is better than most of the existing pattern-based methods and other neural networks based models.

Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction task. Motivated by this, we introduce a deep neural model for learning structure-to-substructure tree transductions by extending the standard Long Short-Term Memory, considering the parent-child relationships in the structural recursion. The proposed model can achieve state of the art performance on sentence compression benchmarks, both in terms of accuracy and compression rate.

Abstract-- The objective is to study an online Hidden Markov model (HMM) estimation-based Q-learning algorithm for partially observable Markov decision process (POMDP) on finite state and action sets. When the full state observation is available, Q-learning finds the optimal action-value function given the current action (Q-function). However, Q-learning can perform poorly when the full state observation is not available. In this paper, we formulate the POMDP estimation into a HMM estimation problem and propose a recursive algorithm to estimate both the POMDP parameter and Q-function concurrently. Also, we show that the POMDP estimation converges to a set of stationary points for the maximum likelihood estimate, and the Q-function estimation converges to a fixed point that satisfies the Bellman optimality equation weighted on the invariant distribution of the state belief determined by the HMM estimation process.

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many situations it is preferable to delay a decision rather than run the risk of making a bad decision. In such situations it is necessary to aggregate information before taking an action; however, most state of the art reinforcement learning (RL) algorithms are biased towards taking actions \textit{at every time step}, even if the agent is not particularly confident in its chosen action. This lack of caution can lead the agent to make critical mistakes, regardless of prior experience and acclimation to the environment. Motivated by theories of dynamic resolution of uncertainty during decision making in biological brains, we propose a simple accumulator module which accumulates evidence in favor of each possible decision, encodes uncertainty as a dynamic competition between actions, and acts on the environment only when it is sufficiently confident in the chosen action. The agent makes no decision by default, and the burden of proof to make a decision falls on the policy to accrue evidence strongly in favor of a single decision. Our results show that this accumulator module achieves near-optimal performance on a simple guessing game, far outperforming deep recurrent networks using traditional, forced action selection policies.

The topic or population polytope (Nguyen, 2015; Tang et al., 2014) is a fundamental geometric object that underlies the presence of latent topic variables in topic and admixture models (Blei et al., 2003; Pritchard et al., 2000). When data and the associated topics are indexed by time dimension, it is of interest to study the temporal dynamics of such latent geometric structures. In this paper, we will study the modeling and algorithms for learning the temporal dynamics of topic polytope that arises in the analysis of text corpora. The convex geometry of topic models provides the theoretical basis for posterior contraction analysis of latent topics (Nguyen, 2015; Tang et al., 2014). Furthermore, Yurochkin & Nguyen (2016); Yurochkin et al. (2017) exploited convex geometry to develop fast and quite accurate inference algorithms in a number of parametric and nonparametric settings.

The representation of knowledge based on first-order logic captures the richness of natural language and supports multiple probabilistic inference models. Although symbolic representation enables quantitative reasoning with statistical probability, it is difficult to utilize with machine learning models as they perform numerical operations. In contrast, knowledge embedding (i.e., high-dimensional and continuous vectors) is a feasible approach to complex reasoning that can not only retain the semantic information of knowledge but also establish the quantifiable relationship among them. In this paper, we propose recursive neural knowledge network (RNKN), which combines medical knowledge based on first-order logic with recursive neural network for multi-disease diagnosis. After RNKN is efficiently trained from manually annotated Chinese Electronic Medical Records (CEMRs), diagnosis-oriented knowledge embeddings and weight matrixes are learned. Experimental results verify that the diagnostic accuracy of RNKN is superior to that of some classical machine learning models and Markov logic network (MLN). The results also demonstrate that the more explicit the evidence extracted from CEMRs is, the better is the performance achieved. RNKN gradually exhibits the interpretation of knowledge embeddings as the number of training epochs increases.

In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms will estimate the value function more accurately and find a better policy. When the state space is large or continuous \emph{Gradient-based Temporal Difference(GTD)} policy evaluation algorithms with linear function approximation are widely used. Considering that the collection of the evaluation data is both time and reward consuming, a clear understanding of the finite sample performance of the policy evaluation algorithms is very important to reinforcement learning. Under the assumption that data are i.i.d. generated, previous work provided the finite sample analysis of the GTD algorithms with constant step size by converting them into convex-concave saddle point problems. However, it is well-known that, the data are generated from Markov processes rather than i.i.d. in RL problems.. In this paper, in the realistic Markov setting, we derive the finite sample bounds for the general convex-concave saddle point problems, and hence for the GTD algorithms. We have the following discussions based on our bounds. (1) With variants of step size, GTD algorithms converge. (2) The convergence rate is determined by the step size, with the mixing time of the Markov process as the coefficient. The faster the Markov processes mix, the faster the convergence. (3) We explain that the experience replay trick is effective by improving the mixing property of the Markov process. To the best of our knowledge, our analysis is the first to provide finite sample bounds for the GTD algorithms in Markov setting.

This paper proposes a method for efficient training of the Q-function for continuous-state Markov Decision Processes (MDP), such that the traces of the resulting policies satisfy a Linear Temporal Logic (LTL) property. The logical property is converted into a limit deterministic Buchi automaton with which a product MDP is constructed. The control policy is then synthesized by a reinforcement learning algorithm assuming that no prior knowledge is available from the MDP. The proposed method is evaluated in a numerical study to test the quality of the generated control policy and is compared against conventional methods for policy synthesis such as MDP abstraction (Voronoi quantizer) and approximate dynamic programming (fitted value iteration).