Related papers: Actor-Free Continuous Control via Structurally Max…
Actor-critic methods can achieve incredible performance on difficult reinforcement learning problems, but they are also prone to instability. This is partly due to the interaction between the actor and critic during learning, e.g., an…
Actor-critic methods are widely used in offline reinforcement learning practice, but are not so well-understood theoretically. We propose a new offline actor-critic algorithm that naturally incorporates the pessimism principle, leading to…
The advances in unsupervised object-centric representation learning have significantly improved its application to downstream tasks. Recent works highlight that disentangled object representations can aid policy learning in image-based,…
Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence…
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…
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence…
This paper introduces and analyzes an improved Q-learning algorithm for discrete-time linear time-invariant systems. The proposed method does not require any knowledge of the system dynamics, and it enjoys significant efficiency advantages…
Recent reinforcement learning approaches have shown surprisingly strong capabilities of bang-bang policies for solving continuous control benchmarks. The underlying coarse action space discretizations often yield favourable exploration…
Q-learning is widely recognized as an effective approach for synthesizing controllers to achieve specific goals. However, handling challenges posed by continuous state-action spaces remains an ongoing research focus. This paper presents a…
Overestimation is a fundamental characteristic of model-free reinforcement learning (MF-RL), arising from the principles of temporal difference learning and the approximation of the Q-function. To address this challenge, we propose a novel…
Reinforcement learning is a general technique that allows an agent to learn an optimal policy and interact with an environment in sequential decision making problems. The goodness of a policy is measured by its value function starting from…
Value factorization is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings, which balances the learning scalability and the representational capacity of value functions. However, the…
The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learning and planning in…
We propose an actor-critic framework to solve the time-continuous stochastic optimal control problem. A least square temporal difference method is applied to compute the value function for the critic. The policy gradient method is…
Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation. In this paper, we propose an implicit actor-critic (iAC)…
Text-based games are a popular testbed for language-based reinforcement learning (RL). In previous work, deep Q-learning is commonly used as the learning agent. Q-learning algorithms are challenging to apply to complex real-world domains…
Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use symmetric architectures, whereby both actor and critic have the same network topology and number of…
We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that offline actor-critic algorithms can outperform strong,…
We present a training framework for neural abstractive summarization based on actor-critic approaches from reinforcement learning. In the traditional neural network based methods, the objective is only to maximize the likelihood of the…
Many real-world control problems, ranging from finance to robotics, evolve in continuous time with non-uniform, event-driven decisions. Standard discrete-time reinforcement learning (RL), based on fixed-step Bellman updates, struggles in…