Related papers: Refined Analysis of Entropy-Regularized Actor-Crit…
Asymmetric actor-critic methods are widely used in partially observable reinforcement learning, but typically assume full state observability to condition the critic during training, which is often unrealistic in practice. We introduce the…
Bandit algorithms are widely used in sequential decision problems to maximize the cumulative reward. One potential application is mobile health, where the goal is to promote the user's health through personalized interventions based on user…
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…
This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm, an extension of the Actor-Critic framework for reducing variance in policy gradient estimation. AISAC optimizes the behavior policy to minimize gradient…
Despite the popularity of the actor-critic method and the practical needs of collaborative policy training, existing works typically either overlook environmental heterogeneity or give up personalization altogether by training a single…
Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional…
Deterministic-policy actor-critic algorithms for continuous control improve the actor by plugging its actions into the critic and ascending the action-value gradient, which is obtained by chaining the actor's Jacobian matrix with the…
\Ac{MPC} and \ac{RL} are two powerful control strategies with, arguably, complementary advantages. In this work, we show how actor-critic \ac{RL} techniques can be leveraged to improve the performance of \ac{MPC}. The \ac{RL} critic is used…
A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number…
Regularization is a core component of recent Reinforcement Learning (RL) algorithms. Mirror Descent Value Iteration (MDVI) uses both Kullback-Leibler divergence and entropy as regularizers in its value and policy updates. Despite its…
Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide…
Soft Actor Critic (SAC) algorithms show remarkable performance in complex simulated environments. A key element of SAC networks is entropy regularization, which prevents the SAC actor from optimizing against fine grained features,…
We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points…
Having a perfect model to compute the optimal policy is often infeasible in reinforcement learning. It is important in high-stakes domains to quantify and manage risk induced by model uncertainties. Entropic risk measure is an exponential…
The hierarchical interaction between the actor and critic in actor-critic based reinforcement learning algorithms naturally lends itself to a game-theoretic interpretation. We adopt this viewpoint and model the actor and critic interaction…
Model-free off-policy actor-critic methods are an efficient solution to complex continuous control tasks. However, these algorithms rely on a number of design tricks and hyperparameters, making their application to new domains difficult and…
Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been…
Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck. These…
Although actor-critic methods have been successful in practice, their theoretical analyses have several limitations. Specifically, existing theoretical work either sidesteps the exploration problem by making strong assumptions or analyzes…
We consider a version of actor-critic which uses proportional step-sizes and only one critic update with a single sample from the stationary distribution per actor step. We provide an analysis of this method using the small-gain theorem.…