Deep reinforcement learning algorithms, including policy gradient methods and Q-learning, have been widely applied to a variety of decision-making problems. Their success has relied heavily on having very well designed dense reward signals, and therefore, they often perform badly on the sparse or episodic reward settings. Trajectory-based policy optimization methods, such as cross-entropy method and evolution strategies, do not take into consideration the temporal nature of the problem and often suffer from high sample complexity. Scaling up the efficiency of RL algorithms to real-world problems with sparse or episodic rewards is therefore a pressing need. In this work, we present a new perspective of policy optimization and introduce a self-imitation learning algorithm that exploits and explores well in the sparse and episodic reward settings. First, we view each policy as a state-action visitation distribution and formulate policy optimization as a divergence minimization problem. Then, we show that, with Jensen-Shannon divergence, this divergence minimization problem can be reduced into a policy-gradient algorithm with dense reward learned from experience replays. Experimental results indicate that our algorithm works comparable to existing algorithms in the dense reward setting, and significantly better in the sparse and episodic settings. To encourage exploration, we further apply the Stein variational policy gradient descent with the Jensen-Shannon kernel to learn multiple diverse policies and demonstrate its effectiveness on a number of challenging tasks.

With the release of ML-Agents v0.3 Beta, there are lots of new ways to use Machine Learning in your projects. Whether you're working on games, simulations, academic or any other sort of projects, your work can benefit from the use of neural networks in the virtual environment. If you've been using ML-Agents before this latest release, you will already be familiar with Reinforcement Learning. If not, I wrote a beginner's guide to get you started. This blog post will help you get up to speed with one of the major features that represent an alternative to Reinforcement Learning: Imitation Learning.

There is another way to categorize the machine learning models above, which is supervised learning (where machine learns from past data that humans have already labeled as good or bad, attack or false positive, fraud or normal data), unsupervised learning (where no past labeled data exist) or reinforcement learning (where machine learns from feedback from its longer-term results). Supervised learning will include classification, regression and deep learning. Unsupervised learning includes clustering, association rules and pattern matching. Diagram 2 will now become diagram 3 below.

The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of reinforcement learning algorithms estimate and/or optimise a proxy for the value function. This proxy is typically based on a sampled and bootstrapped approximation to the true value function, known as a return. The particular choice of return is one of the chief components determining the nature of the algorithm: the rate at which future rewards are discounted; when and how values should be bootstrapped; or even the nature of the rewards themselves. It is well-known that these decisions are crucial to the overall success of RL algorithms. We discuss a gradient-based meta-learning algorithm that is able to adapt the nature of the return, online, whilst interacting and learning from the environment. When applied to 57 games on the Atari 2600 environment over 200 million frames, our algorithm achieved a new state-of-the-art performance.

In industrial environments, an increasing amount of wireless devices are used, which utilize license-free bands. As a consequence of these mutual interferences of wireless systems might decrease the state of coexistence. Therefore, a central coexistence management system is needed, which allocates conflict-free resources to wireless systems. To ensure a conflict-free resource utilization, it is useful to predict the prospective medium utilization before resources are allocated. This paper presents a self-learning concept, which is based on reinforcement learning. A simulative evaluation of reinforcement learning agents based on neural networks, called deep Q-networks and double deep Q-networks, was realized for exemplary and practically relevant coexistence scenarios. The evaluation of the double deep Q-network showed that a prediction accuracy of at least 98 % can be reached in all investigated scenarios.

In recent years, sequence-to-sequence (seq2seq) models are used in a variety of tasks from machine translation, headline generation, text summarization, speech to text, to image caption generation. The underlying framework of all these models are usually a deep neural network which contains an encoder and decoder. The encoder processes the input data and a decoder receives the output of the encoder and generates the final output. Although simply using an encoder/decoder model would, most of the time, produce better result than traditional methods on the above-mentioned tasks, researchers proposed additional improvements over these sequence to sequence models, like using an attention-based model over the input, pointer-generation models, and self-attention models. However, all these seq2seq models suffer from two common problems: 1) exposure bias and 2) inconsistency between train/test measurement. Recently a completely fresh point of view emerged in solving these two problems in seq2seq models by using methods in Reinforcement Learning (RL). In these new researches, we try to look at the seq2seq problems from the RL point of view and we try to come up with a formulation that could combine the power of RL methods in decision-making and sequence to sequence models in remembering long memories. In this paper, we will summarize some of the most recent frameworks that combines concepts from RL world to the deep neural network area and explain how these two areas could benefit from each other in solving complex seq2seq tasks. In the end, we will provide insights on some of the problems of the current existing models and how we can improve them with better RL models. We also provide the source code for implementing most of the models that will be discussed in this paper on the complex task of abstractive text summarization.

We describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of unknown actions on observations while simultaneously predicting their likelihood. We then outline an action alignment procedure that leverages a small amount of environment interactions to determine a mapping between latent and real-world actions. We show that this corrected labeling can be used for imitating the observed behavior, even though no expert actions are given. We evaluate our approach within classic control and photo-realistic visual environments and demonstrate that it performs well when compared to standard approaches.

A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, navigation and self-driving cars. This paper presents the necessary theoretical extensions of Alpha Zero to deal with continuous action space. We also provide some preliminary experiments on the Pendulum swing-up task, empirically showing the feasibility of our approach. Thereby, this work provides a first step towards the application of iterated search and learning in domains with a continuous action space.

In 1848, the 25-year-old Phineas Gage was working on a railroad in Vermont, packing explosive powder into a hole with an iron tamper. Unexpectedly, the powder exploded, sending the tamper backwards through Gage's skull and brain. That he survived is a miracle, but astonishingly he even seemed capable of functioning effectively, maintaining normal memory, speech, and motor skills. Those that knew him, however, thought he was anything but the same, with friends remarking he was "no longer Gage." "…his equilibrium, or balance, so to speak, between his intellectual faculties and animal propensities seems to have been destroyed. He is fitful, irreverent, indulging in the grossest profanity (which was not previously his custom), manifesting but little deference for his fellows, impatient of restraint or advice when it conflicts with his desires."

Efficient exploration is one of the key challenges for reinforcement learning (RL) algorithms. Most traditional sample efficiency bounds require strategic exploration. Recently many deep RL algorithm with simple heuristic exploration strategies that have few formal guarantees, achieve surprising success in many domains. These results pose an important question about understanding these exploration strategies such as $e$-greedy, as well as understanding what characterize the difficulty of exploration in MDPs. In this work we propose problem specific sample complexity bounds of $Q$ learning with random walk exploration that rely on several structural properties. We also link our theoretical results to some empirical benchmark domains, to illustrate if our bound gives polynomial sample complexity or not in these domains and how that is related with the empirical performance in these domains.