arXiv research

This paper introduces CENIE to quantify environment novelty for better UED.

MiniHack simplifies creation of complex RL environments.

AutoDIME automates design of multi-agent environments for RL.

Algorithm optimizes system design and control for better rewards.

Resolves spurious correlations in causal models via intervention design.

In radar systems, unimodular (or constant-modulus) waveform design plays an important role in achieving better clutter/interference rejection, as well as a more accurate estimation of the target parameters. The design of such sequences has been studied widely in the last few decades, with most design algorithms requiri…

Meta-learning improves drone trajectory design for dynamic wireless networks.

Generative thermal design learns optimal shapes using multi-agent reinforcement learning.

A CNN-DRL model improves learning in finance with scalable actions.

Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of the agent's policy can affect its exploration capabilities. First, we design EscapeRoom environments, where the agent must figure out how to n…

We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling. By making a connection between information-theoretic quantities and confidence bounds, we obtain results that relate the per-period performance of the agent with its information gain about the enviro…

FTRL algorithm with negative entropy regularizer achieves best-of-three-world results for linear bandits.

Designers of AI agents often iterate on the reward function in a trial-and-error process until they get the desired behavior, but this only guarantees good behavior in the training environment. We propose structuring this process as a series of queries asking the user to compare between different reward functions. Thus…

As integrated circuits have become progressively more complex, constrained random stimulus has become ubiquitous as a means of stimulating a designs functionality and ensuring it fully meets expectations. In theory, random stimulus allows all possible combinations to be exercised given enough time, but in practice with…

PrototypeML simplifies neural network design and development.

Designs a framework to transfer causal models between similar environments.

This research tackles information design in multi-agent reinforcement learning.

New RL approach learns dynamic VCG mechanisms in unknown MDP environments.

SAMPLR optimizes for ground truth in aleatoric parameters to avoid curriculum-induced covariate shift.

In many reinforcement learning tasks, the goal is to learn a policy to manipulate an agent, whose design is fixed, to maximize some notion of cumulative reward. The design of the agent's physical structure is rarely optimized for the task at hand. In this work, we explore the possibility of learning a version of the ag…

Investigates safe decision-making in interactive environments.

A new method optimizes in nonstationary environments with many arms efficiently.

Deep RL strategies outperform traditional methods in cryptocurrency trading.

Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable effort has gone into addressing opacity, but almost no effort has been devoted t…

New algorithms reduce regret in both stochastic and deterministic environments.

This paper designs a new on-chain option that amortizes perpetual options for blockchain environments.

AI framework for automated policy-making connects with econometrics and social choice.

RID-Noise improves robust design under noisy conditions using neural networks.

UAED discovers adaptive environments for robust learning.

New algorithm improves RL performance across different environments.

PSRL extension for continuing environments reduces regret.

Assisted by neural networks, reinforcement learning agents have been able to solve increasingly complex tasks over the last years. The simulation environment in which the agents interact is an essential component in any reinforcement learning problem. The environment simulates the dynamics of the agents' world and henc…

ReOPD uses pre-collected teacher trajectories to distill knowledge from multi-turn interactions.

Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrins…

The capability to learn and adapt to changes in the driving environment is crucial for developing autonomous driving systems that are scalable beyond geo-fenced operational design domains. Deep Reinforcement Learning (RL) provides a promising and scalable framework for developing adaptive learning based solutions. Deep…

Deep Recurrent Q-Network improves autonomous driving in urban areas with pedestrians.

We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased access to high quality training environments, and we provide detailed experimen…

Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-s…

Optimizes e-commerce traffic sales by incorporating hidden costs into auction mechanisms.

This paper analyzes switchback experiments in A/B testing, revealing key factors affecting their effectiveness.

Dual behavior policy improves reinforcement learning across various environments.

Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in computationally complex environments. In this paper, we propose Asynchronous Episo…

Hierarchical Reinforcement Learning (HRL) exploits temporally extended actions, or options, to make decisions from a higher-dimensional perspective to alleviate the sparse reward problem, one of the most challenging problems in reinforcement learning. The majority of existing HRL algorithms require either significant m…

Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for authors to experiment with self-designed environments, and there are several separate…

Bayesian Invariant Prediction models stable features from multi-environment data.

We present MDP Playground, a testbed for Reinforcement Learning (RL) agents with dimensions of hardness that can be controlled independently to challenge agents in different ways and obtain varying degrees of hardness in toy and complex RL environments. We consider and allow control over a wide variety of dimensions, i…

How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment? We show that current approaches to penalizing side effects can introduce bad incentives, e.g. to prevent any irreversible changes in the environment, including the actions of other agents. To isolate the source…

New algorithm for reinforcement learning in uncertain environments with unknown thresholds.