Balsa: Learning a Query Optimizer Without Expert Demonstrations

Query optimizers are a performance-critical component in every database system. Due to their complexity, optimizers take experts months to write and years to refine. In this work, we demonstrate for the first time that learning to optimize queries without learning from an expert optimizer is both possible and efficient. We present Balsa, a query optimizer built by deep reinforcement learning. Balsa first learns basic knowledge from a simple, environment-agnostic simulator, followed by safe learning in real execution. On the Join Order Benchmark, Balsa matches the performance of two expert query optimizers, both open-source and commercial, with two hours of learning, and outperforms them by up to 2.8$\times$ in workload runtime after a few more hours. Balsa thus opens the possibility of automatically learning to optimize in future compute environments where expert-designed optimizers do not exist.

MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance

Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. However, learning such risk measures requires significant interaction with the environment, resulting in excessive constraint violations during learning. Furthermore, these measures are not easily transferable to new environments. We cast safe exploration as an offline meta-RL problem, where the objective is to leverage examples of safe and unsafe behavior across a range of environments to quickly adapt learned risk measures to a new environment with previously unseen dynamics. We then propose MEta-learning for Safe Adaptation (MESA), an approach for meta-learning a risk measure for safe RL. Simulation experiments across 5 continuous control domains suggest that MESA can leverage offline data from a range of different environments to reduce constraint violations in unseen environments by up to a factor of 2 while maintaining task performance. See https://tinyurl.com/safe-meta-rl for code and supplementary material.

Discovering Non-monotonic Autoregressive Orderings with Variational Inference

The predominant approach for language modeling is to process sequences from left to right, but this eliminates a source of information: the order by which the sequence was generated. One strategy to recover this information is to decode both the content and ordering of tokens. Existing approaches supervise content and ordering by designing problem-specific loss functions and pre-training with an ordering pre-selected. Other recent works use iterative search to discover problem-specific orderings for training, but suffer from high time complexity and cannot be efficiently parallelized. We address these limitations with an unsupervised parallelizable learner that discovers high-quality generation orders purely from training data -- no domain knowledge required. The learner contains an encoder network and decoder language model that perform variational inference with autoregressive orders (represented as permutation matrices) as latent variables. The corresponding ELBO is not differentiable, so we develop a practical algorithm for end-to-end optimization using policy gradients. We implement the encoder as a Transformer with non-causal attention that outputs permutations in one forward pass. Permutations then serve as target generation orders for training an insertion-based Transformer language model. Empirical results in language modeling tasks demonstrate that our method is context-aware and discovers orderings that are competitive with or even better than fixed orders.

Accelerating Quadratic Optimization with Reinforcement Learning

First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapidly solved. These methods face two persistent challenges: manual hyperparameter tuning and convergence time to high-accuracy solutions. To address these, we explore how Reinforcement Learning (RL) can learn a policy to tune parameters to accelerate convergence. In experiments with well-known QP benchmarks we find that our RL policy, RLQP, significantly outperforms state-of-the-art QP solvers by up to 3x. RLQP generalizes surprisingly well to previously unseen problems with varying dimension and structure from different applications, including the QPLIB, Netlib LP and Maros-Meszaros problems. Code for RLQP is available at https://github.com/berkeleyautomation/rlqp.

LazyDAgger: Reducing Context Switching in Interactive Imitation Learning

Corrective interventions while a robot is learning to automate a task provide an intuitive method for a human supervisor to assist the robot and convey information about desired behavior. However, these interventions can impose significant burden on a human supervisor, as each intervention interrupts other work the human is doing, incurs latency with each context switch between supervisor and autonomous control, and requires time to perform. We present LazyDAgger, which extends the interactive imitation learning (IL) algorithm SafeDAgger to reduce context switches between supervisor and autonomous control. We find that LazyDAgger improves the performance and robustness of the learned policy during both learning and execution while limiting burden on the supervisor. Simulation experiments suggest that LazyDAgger can reduce context switches by an average of 60% over SafeDAgger on 3 continuous control tasks while maintaining state-of-the-art policy performance. In physical fabric manipulation experiments with an ABB YuMi robot, LazyDAgger reduces context switches by 60% while achieving a 60% higher success rate than SafeDAgger at execution time.

Distributed Reinforcement Learning is a Dataflow Problem

Researchers and practitioners in the field of reinforcement learning (RL) frequently leverage parallel computation, which has led to a plethora of new algorithms and systems in the last few years. In this paper, we re-examine the challenges posed by distributed RL and try to view it through the lens of an old idea: distributed dataflow. We show that viewing RL as a dataflow problem leads to highly composable and performant implementations. We propose AnonFlow, a hybrid actor-dataflow programming model for distributed RL, and validate its practicality by porting the full suite of algorithms in AnonLib, a widely-adopted distributed RL library.

Connecting Context-specific Adaptation in Humans to Meta-learning

Cognitive control, the ability of a system to adapt to the demands of a task, is an integral part of cognition. A widely accepted fact about cognitive control is that it is context-sensitive: Adults and children alike infer information about a task's demands from contextual cues and use these inferences to learn from ambiguous cues. However, the precise way in which people use contextual cues to guide adaptation to a new task remains poorly understood. This work connects the context-sensitive nature of cognitive control to a method for meta-learning with context-conditioned adaptation. We begin by identifying an essential difference between human learning and current approaches to meta-learning: In contrast to humans, existing meta-learning algorithms do not make use of task-specific contextual cues but instead rely exclusively on online feedback in the form of task-specific labels or rewards. To remedy this, we introduce a framework for using contextual information about a task to guide the initialization of task-specific models before adaptation to online feedback. We show how context-conditioned meta-learning can capture human behavior in a cognitive task and how it can be scaled to improve the speed of learning in various settings, including few-shot classification and low-sample reinforcement learning. Our work demonstrates that guiding meta-learning with task information can capture complex, human-like behavior, thereby deepening our understanding of cognitive control.

Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones

Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm which navigates this tradeoff by (1) leveraging offline data to learn about constraint violating zones before policy learning and (2) separating the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint violation is likely. We evaluate Recovery RL on 6 simulation domains, including two contact-rich manipulation tasks and an image-based navigation task, and an image-based obstacle avoidance task on a physical robot. We compare Recovery RL to 5 prior safe RL methods which jointly optimize for task performance and safety via constrained optimization or reward shaping and find that Recovery RL outperforms the next best prior method across all domains. Results suggest that Recovery RL trades off constraint violations and task successes 2 - 80 times more efficiently in simulation domains and 3 times more efficiently in physical experiments. See https://tinyurl.com/rl-recovery for videos and supplementary material.

IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks

The practical usage of reinforcement learning agents is often bottlenecked by the duration of training time. To accelerate training, practitioners often turn to distributed reinforcement learning architectures to parallelize and accelerate the training process. However, modern methods for scalable reinforcement learning (RL) often tradeoff between the throughput of samples that an RL agent can learn from (sample throughput) and the quality of learning from each sample (sample efficiency). In these scalable RL architectures, as one increases sample throughput (i.e. increasing parallelization in IMPALA), sample efficiency drops significantly. To address this, we propose a new distributed reinforcement learning algorithm, IMPACT. IMPACT extends IMPALA with three changes: a target network for stabilizing the surrogate objective, a circular buffer, and truncated importance sampling. In discrete action-space environments, we show that IMPACT attains higher reward and, simultaneously, achieves up to 30% decrease in training wall-time than that of IMPALA. For continuous control environments, IMPACT trains faster than existing scalable agents while preserving the sample efficiency of synchronous PPO.