Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with exploration by encouraging the selection of more stochastic policies. In this work, we analyze this claim and, through new visualizations of the optimization landscape, we observe that incorporating entropy in policy optimization serves as a regularizer. We show that even with access to the exact gradient, policy optimization is difficult due to the geometry of the objective function. We qualitatively show that, in some environments, entropy regularization can make the optimization landscape smoother, thereby connecting local optima and enabling the use of larger learning rates. This manuscript presents new tools for understanding the underlying optimization landscape and highlights the challenge of designing general-purpose policy optimization algorithms in reinforcement learning.
This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning. To investigate this question, we consider an instantiation of this hypothesis evaluated on the Arcade Learning Element (ALE). In this study, we develop an attentive dynamics model (ADM) that discovers controllable elements of the observations, which are often associated with the location of the character in Atari games. The ADM is trained in a self-supervised fashion to predict the actions taken by the agent. The learned contingency information is used as a part of the state representation for exploration purposes. We demonstrate that combining A2C with count-based exploration using our representation achieves impressive results on a set of notoriously challenging Atari games due to sparse rewards. For example, we report a state-of-the-art score of >6600 points on Montezuma's Revenge without using expert demonstrations, explicit high-level information (e.g., RAM states), or supervised data. Our experiments confirm that indeed contingency-awareness is an extremely powerful concept for tackling exploration problems in reinforcement learning and opens up interesting research questions for further investigations.
We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization tasks. We express the expected return objective as a weighted sum of two terms: an expectation over the high-reward trajectories inside the memory buffer, and a separate expectation over trajectories outside the buffer. To make an efficient algorithm of MAPO, we propose: (1) memory weight clipping to accelerate and stabilize training; (2) systematic exploration to discover high-reward trajectories; (3) distributed sampling from inside and outside of the memory buffer to scale up training. MAPO improves the sample efficiency and robustness of policy gradient, especially on tasks with sparse rewards. We evaluate MAPO on weakly supervised program synthesis from natural language (semantic parsing). On the WikiTableQuestions benchmark, we improve the state-of-the-art by 2.6%, achieving an accuracy of 46.3%. On the WikiSQL benchmark, MAPO achieves an accuracy of 74.9% with only weak supervision, outperforming several strong baselines with full supervision. Our source code is available at https://github.com/crazydonkey200/neural-symbolic-machines
Sequence to sequence (SEQ2SEQ) models often lack diversity in their generated translations. This can be attributed to the limitation of SEQ2SEQ models in capturing lexical and syntactic variations in a parallel corpus resulting from different styles, genres, topics, or ambiguity of the translation process. In this paper, we develop a novel sequence to sequence mixture (S2SMIX) model that improves both translation diversity and quality by adopting a committee of specialized translation models rather than a single translation model. Each mixture component selects its own training dataset via optimization of the marginal loglikelihood, which leads to a soft clustering of the parallel corpus. Experiments on four language pairs demonstrate the superiority of our mixture model compared to a SEQ2SEQ baseline with standard or diversity-boosted beam search. Our mixture model uses negligible additional parameters and incurs no extra computation cost during decoding.
We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance. OCD is efficient, has no hyper-parameters of its own, and does not require pretraining or joint optimization with conditional log-likelihood. Given a partial sequence generated by the model, we first identify the set of optimal suffixes that minimize the total edit distance, using an efficient dynamic programming algorithm. Then, for each position of the generated sequence, we use a target distribution that puts equal probability on the first token of all the optimal suffixes. OCD achieves the state-of-the-art performance on end-to-end speech recognition, on both Wall Street Journal and Librispeech datasets, achieving $9.3\%$ WER and $4.5\%$ WER respectively.
Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating sentences one token at a time from left to right. This paper studies the influence of token generation order on model quality via a novel two-pass language model that produces partially-filled sentence "templates" and then fills in missing tokens. We compare various strategies for structuring these two passes and observe a surprisingly large variation in model quality. We find the most effective strategy generates function words in the first pass followed by content words in the second. We believe these experimental results justify a more extensive investigation of generation order for neural language models.
State-action value functions (i.e., Q-values) are ubiquitous in reinforcement learning (RL), giving rise to popular algorithms such as SARSA and Q-learning. We propose a new notion of action value defined by a Gaussian smoothed version of the expected Q-value. We show that such smoothed Q-values still satisfy a Bellman equation, making them learnable from experience sampled from an environment. Moreover, the gradients of expected reward with respect to the mean and covariance of a parameterized Gaussian policy can be recovered from the gradient and Hessian of the smoothed Q-value function. Based on these relationships, we develop new algorithms for training a Gaussian policy directly from a learned smoothed Q-value approximator. The approach is additionally amenable to proximal optimization by augmenting the objective with a penalty on KL-divergence from a previous policy. We find that the ability to learn both a mean and covariance during training leads to significantly improved results on standard continuous control benchmarks.
This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single image, KeypointNet extracts 3D keypoints that are optimized for a downstream task. We demonstrate this framework on 3D pose estimation by proposing a differentiable objective that seeks the optimal set of keypoints for recovering the relative pose between two views of an object. Our model discovers geometrically and semantically consistent keypoints across viewing angles and instances of an object category. Importantly, we find that our end-to-end framework using no ground-truth keypoint annotations outperforms a fully supervised baseline using the same neural network architecture on the task of pose estimation. The discovered 3D keypoints on the car, chair, and plane categories of ShapeNet are visualized at http://keypointnet.github.io/.
Natural language text exhibits hierarchical structure in a variety of respects. Ideally, we could incorporate our prior knowledge of this hierarchical structure into unsupervised learning algorithms that work on text data. Recent work by Nickel & Kiela (2017) proposed using hyperbolic instead of Euclidean embedding spaces to represent hierarchical data and demonstrated encouraging results when embedding graphs. In this work, we extend their method with a re-parameterization technique that allows us to learn hyperbolic embeddings of arbitrarily parameterized objects. We apply this framework to learn word and sentence embeddings in hyperbolic space in an unsupervised manner from text corpora. The resulting embeddings seem to encode certain intuitive notions of hierarchy, such as word-context frequency and phrase constituency. However, the implicit continuous hierarchy in the learned hyperbolic space makes interrogating the model's learned hierarchies more difficult than for models that learn explicit edges between items. The learned hyperbolic embeddings show improvements over Euclidean embeddings in some -- but not all -- downstream tasks, suggesting that hierarchical organization is more useful for some tasks than others.
We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC). The algorithm operates in $K$ stages of parallel function evaluations and trains a cascade of binary classifiers to iteratively cull the undesirable regions of the search space. SHAC is easy to implement, requires no tuning of its own configuration parameters, is invariant to the scale of the objective function and can be built using any choice of binary classifier. We adopt tree-based classifiers within SHAC and achieve competitive performance against several strong baselines for optimizing synthetic functions, hyperparameters and architectures.