arXiv research

Foundation models struggle with multi-turn exploration but can learn through regular summaries.

We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science. As of June 20th 2019, the dataset comprises of 12 quantum mechanical properties of 119,487 organic molecules with up to 14 heavy atoms, sampled from the GDB MedChem database. The Alchemy…

Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.

Motivated by the need for parametric families of rich and yet tractable distributions in financial mathematics, both in pricing and risk management settings, but also considering wider statistical applications, we investigate a novel technique for introducing skewness or kurtosis into a symmetric or other distribution.…

Machine learning models are vulnerable to adversarial inputs that induce seemingly unjustifiable errors. As automated classifiers are increasingly used in industrial control systems and machinery, these adversarial errors could grow to be a serious problem. Despite numerous studies over the past few years, the field of…

Two algorithms improve Federated RL in diverse environments.

OBSER framework infers sub-environments from objects, outperforming scene-based methods.

UAED discovers adaptive environments for robust learning.

New approach handles stochastic and partially-observable environments using discrete autoencoders and Monte Carlo tree search.

Self-supervised policy adapts after deployment without rewards.

Bayesian model for multi-environment prediction with latent variable changes.

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

We consider apprenticeship learning, i.e., having an agent learn a task by observing an expert demonstrating the task in a partially observable environment when the model of the environment is uncertain. This setting is useful in applications where the explicit modeling of the environment is difficult, such as a dialog…

Infinite hierarchical contrastive clustering identifies personal environments linked to health outcomes.

Research shows collective learning across diverse environments is hard due to privacy and security concerns.

LEADS improves model generalization across different environments.

A new method shapes reinforcement learning environments by abstracting large state spaces.

In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of complicated policies. Since the views may frequently suffer from partial observabilit…

MiniHack simplifies creation of complex RL environments.

WILD-SCAV benchmarks AI in complex 3D FPS environments.

Reinforcement learning aims at searching the best policy model for decision making, and has been shown powerful for sequential recommendations. The training of the policy by reinforcement learning, however, is placed in an environment. In many real-world applications, however, the policy training in the real environmen…

PSRL extension for continuing environments reduces regret.

New method learns robust representations by modeling environment variation.

GALA framework learns invariant graph representations via environment augmentation with minimal assumptions.

Reinforcement learning (RL) methods learn optimal decisions in the presence of a stationary environment. However, the stationary assumption on the environment is very restrictive. In many real world problems like traffic signal control, robotic applications, one often encounters situations with non-stationary environme…

We discuss a variant of Thompson sampling for nonparametric reinforcement learning in a countable classes of general stochastic environments. These environments can be non-Markov, non-ergodic, and partially observable. We show that Thompson sampling learns the environment class in the sense that (1) asymptotically its …

XRM discovers environments without human annotations for OOD methods.

ATLAS separates invariant and transferable latent factors across diverse environments.

In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial observability, their level of importance are often different. In this paper, we propose a dee…

Learning in a non-stationary environment is an inevitable problem when applying machine learning algorithm to real world environment. Learning new tasks without forgetting the previous knowledge is a challenge issue in machine learning. We propose a Kalman Filter based modifier to maintain the performance of Neural Net…

Researchers use DT to transfer policies from one environment to another using causal reasoning.

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic envi…

New algorithm guarantees domain generalization with few environments.

NetHack Learning Environment (NLE) tests RL algorithms, offering scalable, complex, and challenging gameplay.

This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel continual learning method of incremental learning, where a challenging environment is solved using o…

The paper formalizes robot environments using topological concepts.

New algorithm improves model generalization in structured biomedical domains.

An agent explores indefinitely in an environment with unlimited rewards.

New model-based methods adapt pre-trained policies to unseen environments efficiently.

Study on estimating causal effects with limited data and multiple environments.

Meta-learners estimate CATE from multiple environments with partial identification.

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…

Algorithm learns from offline data to improve performance in target environment.

Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we present an algorithm for learning object models of non-stationary objects found in office-type environments. Our algorithm exp…

Self-supervised methods, wherein an agent learns representations solely by observing the results of its actions, become crucial in environments which do not provide a dense reward signal or have labels. In most cases, such methods are used for pretraining or auxiliary tasks for "downstream" tasks, such as control, expl…

Analyzes non-Markovian environments in stochastic approximation.

New method uses unlabeled data to improve model robustness across different environments.

Paper argues context equals environment, improving AI generalization.