arXiv research

Embedding RL policies in RKHS for robustness and theoretical guarantees.

CPME embeds counterfactual outcomes in RKHS for flexible policy evaluation.

New algorithm tackles dynamic query routing to multiple embedding models.

New method learns state embeddings from demonstrations for improved reinforcement learning.

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. Distributions over states given the observations are obtained by applying the kernel Bayes' …

New estimator GMIPS reduces variance in ranking policy evaluation.

We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamics and goals. The resulting policies are parametrized by shared parameters that allow for transfer between different dynamics and goal condit…

In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment's dynamics, enabling e…

New OPE estimator improves offline policy evaluation for large action spaces.

New method improves reinforcement learning generalization.

A new method estimates multi-dimensional value distributions using Hilbert space embeddings.

CAEL-MIPS learns embeddings to improve MIPS for better OPE in contextual bandits.

In hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play from Sukhbaatar et al. (2018), that automatically learns a good representation of sub-goals in the environment and a low-level policy that can…

Foreign policy analysis has been struggling to find ways to measure policy preferences and paradigm shifts in international political systems. This paper presents a novel, potential solution to this challenge, through the application of a neural word embedding (Word2vec) model on a dataset featuring speeches by heads o…

The ability to transfer in reinforcement learning is key towards building an agent of general artificial intelligence. In this paper, we consider the problem of learning to simultaneously transfer across both environments (ENV) and tasks (TASK), probably more importantly, by learning from only sparse (ENV, TASK) pairs …

This paper introduces a new method to evaluate multiple policies simultaneously.

The paper tackles counterfactual learning for stochastic policies with continuous actions.

Develops HMRL for sparse reward RL problems, improving meta policy efficiency and transferability.

Generative neural nets learn deep policies conditioned on goals.

SymNet uses neural models to solve RMDPs efficiently.

CoinDICE estimates confidence intervals for unknown behavior policies in reinforcement learning.

Bayesian approach for modeling counterfactual distribution and off-policy evaluation.

Proposes MDR estimator for unbiased OPE with large action spaces.

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…

We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiab…

This paper optimizes off-policy evaluation in reinforcement learning with function approximation.

Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from scratch for each new problem. To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on othe…

New RL method learns value function for many policies using few key states.

New model combines neural networks and embeddings for better choice modeling interpretability.

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

Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training…

This paper examines linear embeddings for high-dimensional Bayesian optimization, identifying and addressing issues to improve performance.

Galen algorithm compresses neural networks for specific hardware with reduced latency.

Temporal point process is an expressive tool for modeling event sequences over time. In this paper, we take a reinforcement learning view whereby the observed sequences are assumed to be generated from a mixture of latent policies. The purpose is to cluster the sequences with different temporal patterns into the underl…

New framework learns policies for partially observable systems.

Entangled bisimulation improves policy learning from visual input.

Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL…

Mixed RL improves RL efficiency with dual representations.

A new benchmark task for evaluating policy learning in complex, high-dimensional action spaces.

NPMD uses CNNs to optimize policies on low-dimensional manifolds, reducing sample complexity.

Model-free reinforcement learning algorithms such as Deep Deterministic Policy Gradient (DDPG) often require additional exploration strategies, especially if the actor is of deterministic nature. This work evaluates the use of model-based trajectory optimization methods used for exploration in Deep Deterministic Policy…

NDPs embed dynamical systems into neural networks for efficient sensorimotor learning.

A major challenge in reinforcement learning (RL) is the design of agents that are able to generalize across tasks that share common dynamics. A viable solution is meta-reinforcement learning, which identifies common structures among past tasks to be then generalized to new tasks (meta-test). In meta-training, the RL ag…

Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algo…

Two algorithms improve Federated RL in diverse environments.

DAGR improves navigation by refining goal representations conditioned on the current state.

New framework for RL transfer learning with state-action mismatch.

Study improves U.S. monetary policy forecasting by integrating text and data.