A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word level (tagging, parsing tasks) or sentence level (question answering, machine translation). This kind of supervision is not realistic of how humans learn, where language is both learned by, and used for, communication. In this work, we study dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation. We study this setup in two domains: the bAbI dataset of (Weston et al., 2015) and large-scale question answering from (Dodge et al., 2015). We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher's response. In particular, a surprising result is that it can learn to answer questions correctly without any reward-based supervision at all.

Existing object proposal algorithms usually search for possible object regions over multiple locations and scales \emph{ separately}, which ignore the interdependency among different objects and deviate from the human perception procedure. To incorporate global interdependency between objects into object localization, we propose an effective Tree-structured Reinforcement Learning (Tree-RL) approach to sequentially search for objects by fully exploiting both the current observation and historical search paths. The Tree-RL approach learns multiple searching policies through maximizing the long-term reward that reflects localization accuracies over all the objects. Starting with taking the entire image as a proposal, the Tree-RL approach allows the agent to sequentially discover multiple objects via a tree-structured traversing scheme. Allowing multiple near-optimal policies, Tree-RL offers more diversity in search paths and is able to find multiple objects with a single feed-forward pass. Therefore, Tree-RL can better cover different objects with various scales which is quite appealing in the context of object proposal. Experiments on PASCAL VOC 2007 and 2012 validate the effectiveness of the Tree-RL, which can achieve comparable recalls with current object proposal algorithms via much fewer candidate windows.

Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional distributions. In such problems, each sample $x$ itself is associated with a conditional distribution $p(z|x)$ represented by samples $\{z_i\}_{i=1}^M$, and the goal is to learn a function $f$ that links these conditional distributions to target values $y$. These learning problems become very challenging when we only have limited samples or in the extreme case only one sample from each conditional distribution. Commonly used approaches either assume that $z$ is independent of $x$, or require an overwhelmingly large samples from each conditional distribution. To address these challenges, we propose a novel approach which employs a new min-max reformulation of the learning from conditional distribution problem. With such new reformulation, we only need to deal with the joint distribution $p(z,x)$. We also design an efficient learning algorithm, Embedding-SGD, and establish theoretical sample complexity for such problems. Finally, our numerical experiments on both synthetic and real-world datasets show that the proposed approach can significantly improve over the existing algorithms.

Temporal Difference learning or TD($\lambda$) is a fundamental algorithm in the field of reinforcement learning. However, setting TD's $\lambda$ parameter, which controls the timescale of TD updates, is generally left up to the practitioner. We formalize the $\lambda$ selection problem as a bias-variance trade-off where the solution is the value of $\lambda$ that leads to the smallest Mean Squared Value Error (MSVE). To solve this trade-off we suggest applying Leave-One-Trajectory-Out Cross-Validation (LOTO-CV) to search the space of $\lambda$ values. Unfortunately, this approach is too computationally expensive for most practical applications. For Least Squares TD (LSTD) we show that LOTO-CV can be implemented efficiently to automatically tune $\lambda$ and apply function optimization methods to efficiently search the space of $\lambda$ values. The resulting algorithm, ALLSTD, is parameter free and our experiments demonstrate that ALLSTD is significantly computationally faster than the na\"{i}ve LOTO-CV implementation while achieving similar performance.

In second place, Ng saw neither unsupervised learning nor reinforcement learning, but transfer learning. One of the hottest developments within Deep Learning was Generative Adversarial Networks (GANs). Secondly, end-to-end (supervised) Deep Learning allows us to learn to map from inputs directly to outputs. The Conference on Neural Information Processing Systems (NIPS) is one of the two top conferences in machine learning. Among ML research areas, supervised learning is the undisputed driver of the recent success of ML and will likely continue to drive it for the foreseeable future.

Learning to learn by gradient descent by gradient descent

This paper investigates a type of instability that is linked to the greedy policy improvement in approximated reinforcement learning. We show empirically that non-deterministic policy improvement can stabilize methods like LSPI by controlling the improvements' stochasticity. Additionally we show that a suitable representation of the value function also stabilizes the solution to some degree. The presented approach is simple and should also be easily transferable to more sophisticated algorithms like deep reinforcement learning.

Mini World of Bits ("MiniWoB") is a benchmark for reinforcement learning agents who interact with websites. The agents perceive the raw pixels of a small (210x160 pixel) webpage and produce keyboard and mouse actions. The environments are written in HTML/Javascript/CSS and are designed to test the agent's capacity to interact with common web browser elements, such as buttons, text fields, slides, date pickers, etc. The environments of this benchmark are accessible through the OpenAI Universe. Each environment is an HTML page that is 210 pixels high, 160px wide (i.e.

Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. In this paper, we present 3 methods for reducing the number of dialogs required to optimize an RNN-based dialog policy with RL. The key idea is to maintain a second RNN which predicts the value of the current policy, and to apply experience replay to both networks. On two tasks, these methods reduce the number of dialogs/episodes required by about a third, vs. standard policy gradient methods.

I'd love to see us advance these new ideas, whether its memory, reinforcement learning, or transfer learning, unsupervised learning. Deep learning has certainly been successful, but it's only a very approximate simulation of what goes on in the brain. All of these areas of research will expand the capabilities of this tool called deep learning dramatically. Deep learning has given us an algorithm that can finally allow robots to learn for themselves, from high-level goals, and through iteration discover for itself. Nvidia's CEO says his hardware will revolutionize robotics and that his chips can learn from Google's AlphaGo.