arXiv research

Improves reinforcement learning stability and efficiency.

New algorithm stabilizes RL policy learning through divergence regularization.

The paper shows how to stabilize off-policy reinforcement learning using specific state representations.

New algorithms improve policy evaluation in reinforcement learning.

Stabilizes policy optimization with off-policy data using divergence augmentation.

Adapts GRPO for off-policy RL, improving reward.

Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true value function $V$. Two novel algorithms are proposed to approximate the true value…

New method stabilizes FQE by reweighting Bellman targets.

Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and actor-critic methods are highly sensitive to the data distribution, and can make only …

Unified DICE estimators as regularized Lagrangians for improved off-policy evaluation.

The paper introduces a novel method for stable off-policy learning using value function chaining.

New algorithm reduces bias in off-policy reinforcement learning.

Off-policy evaluation (OPE) in both contextual bandits and reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. The problem's importance has attracted many proposed solutions, including importance sampling (IS), self…

ADAC uses analogous policies to improve RL exploration without sacrificing stability.

A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.

In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of algorithms makes it difficult to discern which particular approach would be best …

Study shows refugee matching gains are robust to different evaluation methods.

Cramming method evaluates learned policies from contextual bandits efficiently.

New algorithms improve reinforcement learning stability and performance.

FFN addresses spectral bias in neural value approximation, improving reinforcement learning performance.

New TD algorithms stabilize RL tasks by reformulating updates into fixed point equations.

This study improves convergence of two-timescale SA under Markovian noise in reinforcement learning.

Deep Reinforcement Learning (DRL) algorithms for continuous action spaces are known to be brittle toward hyperparameters as well as \cut{being}sample inefficient. Soft Actor Critic (SAC) proposes an off-policy deep actor critic algorithm within the maximum entropy RL framework which offers greater stability and empiric…

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy ($π$) and the behavior policy (b) is a major cause of instability. High variance also originates from distributional mismatch. The var…

This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Mark…

We investigate the combination of actor-critic reinforcement learning algorithms with uniform large-scale experience replay and propose solutions for two challenges: (a) efficient actor-critic learning with experience replay (b) stability of off-policy learning where agents learn from other agents behaviour. We employ …

Enhances RL by controlling policy stochasticity through trajectory entropy constraints.

Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample complexity and brittleness to hyperparameters. Both of these challenges limit the a…

Evolutionary Strategies optimize hyper-parameters for off-policy learning.

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy …

This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-…

Memory-efficient algorithm reduces variance in off-policy RL.

Paper improves bootstrapping for off-policy reinforcement learning inference.

We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities. We prove that such approximate corrections are sufficien…

Adaptive inference for $M$-estimators in bandit data with model misspecification.

Proposes a method to improve treatment policies in data-scarce clinical settings.

Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due to past data available in the replay buffer that may be quite different from th…

Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new technique that combines policy gradient with off-policy Q-learning, drawing experie…

RO-TD learns sparse value functions efficiently.

Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy improvement is guaranteed from on- and off-policy mixture samples. An optimization …

The principal contribution of this paper is a conceptual framework for off-policy reinforcement learning, based on conditional expectations of importance sampling ratios. This framework yields new perspectives and understanding of existing off-policy algorithms, and reveals a broad space of unexplored algorithms. We th…

New algorithm for sequential off-policy learning improves performance over batch methods.

Paper proposes a framework for reliable off-policy evaluation in reinforcement learning.

Novel LSE estimator improves off-policy learning and evaluation.

We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In particular, we introduce a novel doubly-robust estimator for the OPE problem in RL, b…

We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what …

Method selects best estimator for off-policy evaluation.

OSIRIS reduces variance in off-policy evaluation by omitting irrelevant states.