A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
JPS improves joint policies for multi-agent collaboration in imperfect information games.
Galen algorithm compresses neural networks for specific hardware with reduced latency.
APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.
Robotic table tennis learns efficient policies to return balls at 100Hz.
Algorithm optimizes system design and control for better rewards.
Previous work has shown that popular trending events are important external factors which pose significant influence on user search behavior and also provided a way to computationally model this influence. However, their problem formulation was based on the strong assumption that each event poses its influence independ…
Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online. During search, the simulation policy is adapted to explore the most promising lines of play. MCTS has been used by state-of-the-art programs for many problems, however a disadvantage to MCTS is that it estimates the va…
A new method reduces variance in training early-stage rankers for large-scale search systems.
VPP learns joint policies for multi-agent RL through interactions.
MA-COPP predicts multi-agent system outcomes using data from a different policy, with probabilistic guarantees.
Bayesian approach for policy search in stochastic domains.
JES optimizes expensive functions by considering joint entropy over input and output spaces.
Enhances RL performance with a population-guided parallel learning scheme.
Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a st…
We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that are parameterized in a way that makes them easily reusable. This diversity and p…
Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning from high-dimensional context variables, such as camera images, is still a prominent problem in many real-world tasks. A naive application o…
Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the reference policy is suboptimal and the goal of learning is to improve upon it. Ca…
Learning policies on data synthesized by models can in principle quench the thirst of reinforcement learning algorithms for large amounts of real experience, which is often costly to acquire. However, simulating plausible experience de novo is a hard problem for many complex environments, often resulting in biases for …
Proposes baselines for joint NAS and HPO optimization.
Paper shows MCTS approximates policy optimization, proposing an improved variant.
Simple policy search outperforms advanced learnable test-time augmentation techniques.
Paper proposes MCTSPO for better reinforcement learning policy optimization.
We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes. Our approach samples candidate models from the multinomial distribution on the policy vectors defined on the two search spaces independently. The proposed technique improves the eff…
New methods use vector search and nearest-neighbor matching for policy learning in causal inference.
Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different task contexts. Contextual policy search offers data-efficient learning and generalization by explicitly conditioning the policy on a parametric context space. In this paper…
Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam. We develop an unifying meta-algorithm for learning beam search policies using imitation learning.…
Early stopping method saves up to 75% computation time in policy search tasks.
In quadruped gait learning, policy search methods that scale high dimensional continuous action spaces are commonly used. In most approaches, it is necessary to introduce prior knowledge on the gaits to limit the highly non-convex search space of the policies. In this work, we propose a new approach to encode the symme…
Bayesian optimization improves policy search in reinforcement learning.
This paper improves self-play learning in games by manipulating experience distributions.
Transformer learns to search through reinforcement learning, mimicking DFS.
Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.
Contextual policy search allows adapting robotic movement primitives to different situations. For instance, a locomotion primitive might be adapted to different terrain inclinations or desired walking speeds. Such an adaptation is often achievable by modifying a small number of hyperparameters. However, learning, when …
While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few …
Study improves policy search in continuous control by using heavy-tailed distributions.
New method learns better branching policies for MILP problems.
We introduce a multimodal visual-textual search refinement method for fashion garments. Existing search engines do not enable intuitive, interactive, refinement of retrieved results based on the properties of a particular product. We propose a method to retrieve similar items, based on a query item image and textual re…
A major problem in data augmentation is to ensure that the generated new samples cover the search space. This is a challenging problem and requires exploration for data augmentation policies to ensure their effectiveness in covering the search space. In this paper, we propose Greedy AutoAugment as a highly efficient se…
We study the problem of learning a good search policy for combinatorial search spaces. We propose retrospective imitation learning, which, after initial training by an expert, improves itself by learning from \textit{retrospective inspections} of its own roll-outs. That is, when the policy eventually reaches a feasible…
Extends NAS to learn both intra-cell and inter-cell architectures for language modeling.
Traditional model-based reinforcement learning approaches learn a model of the environment dynamics without explicitly considering how it will be used by the agent. In the presence of misspecified model classes, this can lead to poor estimates, as some relevant available information is ignored. In this paper, we introd…
RODE learns roles to simplify multi-agent tasks.
The paper proposes an interpretable off-policy learning algorithm for medical treatments.
Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different "contexts". Bayesian optimization approaches to contextual policy search (CPS) offer data-efficient policy learning that generalize over a context space. We propose to impr…
Optimizes Thompson sampling policies using policy gradient methods.
We report a neural architecture search framework, BioNAS, that is tailored for biomedical researchers to easily build, evaluate, and uncover novel knowledge from interpretable deep learning models. The introduction of knowledge dissimilarity functions in BioNAS enables the joint optimization of predictive power and bio…
CODA resolves coordination issues in offline multi-agent reinforcement learning.
Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to the real world. Several existing approaches involve sampling large batches of traj…