Related papers: $\pi2\text{vec}$: Policy Representations with Succ…

Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the…

Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage.…

Off-policy evaluation is a key component of reinforcement learning which evaluates a target policy with offline data collected from behavior policies. It is a crucial step towards safe reinforcement learning and has been used in…

Vector representations of graphs and relational structures, whether hand-crafted feature vectors or learned representations, enable us to apply standard data analysis and machine learning techniques to the structures. A wide range of…

We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on conservatism in policy design, DOM2 enhances policy expressiveness…

In tabular case, when the reward and environment dynamics are known, policy evaluation can be written as $\bm{V}_{\bm{\pi}} = (I - \gamma P_{\bm{\pi}})^{-1} \bm{r}_{\bm{\pi}}$, where $P_{\bm{\pi}}$ is the state transition matrix given…

Machine learning models are trained with relatively simple objectives, such as next token prediction. However, on deployment, they appear to capture a more fundamental representation of their input data. It is of interest to understand the…

Use cases of sentiment analysis in the humanities often require contextualized, continuous scores. Concept Vector Projections (CVP) offer a recent solution: by modeling sentiment as a direction in embedding space, they produce continuous,…

A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces.…

Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…

In Reinforcement Learning (RL), training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration. Recently, offline RL provides a promising solution by giving an initialized offline…

Various text analysis techniques exist, which attempt to uncover unstructured information from text. In this work, we explore using statistical dependence measures for textual classification, representing text as word vectors. Student…

This paper provides an outline of a formal approach that we are developing for modelling Virtual Organisations (VOs) and their Breeding Environments (VBEs). We propose different levels of representation for the functional structures and…

One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature…

Open-vocabulary state tracking is a more practical version of state tracking that aims to track state changes of entities throughout a process without restricting the state space and entity space. OpenPI is to date the only dataset…

Deep policy networks enable robots to learn behaviors to solve various real-world complex tasks in an end-to-end fashion. However, they lack transparency to provide the reasons of actions. Thus, such a black-box model often results in low…

Model inversion attacks pose a significant privacy risk by attempting to reconstruct private training data from trained models. Most of the existing methods either depend on gradient estimation or require white-box access to model…

Probabilistic modeling is cyclical: we specify a model, infer its posterior, and evaluate its performance. Evaluation drives the cycle, as we revise our model based on how it performs. This requires a metric. Traditionally, predictive…

Predicting protein interactions is one of the more interesting challenges of the post-genomic era. Many algorithms address this problem as a binary classification problem: given two proteins represented as two vectors of features, predict…

Most reinforcement learning practitioners evaluate their policies with online Monte Carlo estimators for either hyperparameter tuning or testing different algorithmic design choices, where the policy is repeatedly executed in the…