arXiv research

AQL uses amortized inference to handle high-dimensional action spaces in Q-learning.

Method trains neural network for optimal decisions from stochastic simulators.

SDM Policy accelerates inference for robotic tasks while maintaining high action quality.

Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning. These methods infer a goal or reward function that best explains the actions of the observed agent, typically a human demonstrator. Another agent can use this infer…

New methods use vector search and nearest-neighbor matching for policy learning in causal inference.

Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a more realistic and difficult scenario where a reinforcement learning agent only has access to the state sequences of an expert, while the expe…

TRAiL is a linear bandit algorithm that ensures optimal regret and guarantees inference quality.

AR CI framework handles complex confounders and sequential actions.

Unified reinforcement learning and stochastic processes with action-driven processes.

This paper improves causal inference using deep neural networks for low-dimensional covariates.

Agent uses message passing to optimize robot navigation, balancing exploration and exploitation.

GIM learns by analogy to improve reinforcement learning efficiency.

New method minimizes decision errors in large treatment spaces.

AG-RL uses action grammars to improve reinforcement learning efficiency.

Active inference selects actions to maximize information gain, aiding structure learning.

Bayesian framework for learning optimal action-value function in MDPs.

New method learns robot actions from videos without explicit labels.

Enhances PlaNet for better planning in uncertain environments.

Efficient Bayesian decision-making with intractable likelihoods.

Deep learning enhances active inference for dynamic state spaces.

Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be decomposed into a component that acts in a low-dimensional space of action represen…

Bayesian inference over admissible histories leads to irreversible kinetics.

Using the theory of group action, we first introduce the concept of the automorphism group of an exponential family or a graphical model, thus formalizing the general notion of symmetry of a probabilistic model. This automorphism group provides a precise mathematical framework for lifted inference in the general expone…

New reinforcement learning framework for adapting to new actions.

PSI-LinUCB improves scalability for large recommender systems.

SLHF uses sequential game theory to optimize preferences from human feedback.

Robots learn actions and language through curiosity-driven self-exploration.

Paper proposes a new HMM approach for better action recognition.

In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied in the lifelong learning literature, the setting where the action set…

This work frames active inference through control as inference, offering robust control algorithms.

New method identifies how platforms can influence consumer behavior.

We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen tasks are not provided. To perform well, the policy must infer the tas…

New comparison shows differences in how value is incorporated in AIF and CAI.

A textbook on machine learning explaining patterns, predictions, and actions.

Recently, it has been shown how sampling actions from the predictive distribution over the optimal action-sometimes called Thompson sampling-can be applied to solve sequential adaptive control problems, when the optimal policy is known for each possible environment. The predictive distribution can then be constructed b…

Model-based planning holds great promise for improving both sample efficiency and generalization in reinforcement learning (RL). We show that energy-based models (EBMs) are a promising class of models to use for model-based planning. EBMs naturally support inference of intermediate states given start and goal state dis…

HO2 learns options from data efficiently, improving robot manipulation tasks.

In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while simultaneously predicting their likelihood. We then outline an action alignment procedure th…

Deep active inference agents learn complex environments using Monte-Carlo methods.

This work presents a game-theoretic method for AVs that handles imperfect communication and individual rewards.

Deep active inference learns policies from sensory inputs.

This paper proposes a novel approach for constructing effective personalized policies when the observed data lacks counter-factual information, is biased and possesses many features. The approach is applicable in a wide variety of settings from healthcare to advertising to education to finance. These settings have in c…

We propose a Variational Time Series Feature Extractor (VTSFE), inspired by the VAE-DMP model of Chen et al., to be used for action recognition and prediction. Our method is based on variational autoencoders. It improves VAE-DMP in that it has a better noise inference model, a simpler transition model constraining the …

Paper shows how to infer hidden states in neural networks analytically.

Inverse reinforcement learning (IRL) aims to explain observed strategic behavior by fitting reinforcement learning models to behavioral data. However, traditional IRL methods are only applicable when the observations are in the form of state-action paths. This assumption may not hold in many real-world modeling setting…

This paper solves the normalizability crisis in sequential inference by introducing bounded information geometry.

The paper models user-advertiser interactions using point processes.

In many biomedical, science, and engineering problems, one must sequentially decide which action to take next so as to maximize rewards. One general class of algorithms for optimizing interactions with the world, while simultaneously learning how the world operates, is the multi-armed bandit setting and, in particular,…