Related papers: A Batch, Off-Policy, Actor-Critic Algorithm for Op…
We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for…
Model-free deep reinforcement learning (RL) algorithms have been demonstrated on a range of challenging decision making and control tasks. However, these methods typically suffer from two major challenges: very high sample complexity and…
Efficient utilization of the replay buffer plays a significant role in the off-policy actor-critic reinforcement learning (RL) algorithms used for model-free control policy synthesis for complex dynamical systems. We propose a method for…
Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function…
Reinforcement learning algorithms have had tremendous successes in online learning settings. However, these successes have relied on low-stakes interactions between the algorithmic agent and its environment. In many settings where RL could…
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize…
Reinforcement learning algorithms are known to be sample inefficient, and often performance on one task can be substantially improved by leveraging information (e.g., via pre-training) on other related tasks. In this work, we propose a…
In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently…
Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the actor's current policy. However, despite their stability…
Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks. Normally, the critic's action-value function is updated using temporal-difference, and the critic in turn provides a loss for the…
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…
In cooperative stochastic games multiple agents work towards learning joint optimal actions in an unknown environment to achieve a common goal. In many real-world applications, however, constraints are often imposed on the actions that can…
In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action…
In many settings, a decision-maker wishes to learn a rule, or policy, that maps from observable characteristics of an individual to an action. Examples include selecting offers, prices, advertisements, or emails to send to consumers, as…
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 develop a generic data-driven method for estimator selection in off-policy policy evaluation settings. We establish a strong performance guarantee for the method, showing that it is competitive with the oracle estimator, up to a constant…
Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…
Model-free deep reinforcement learning has achieved great success in many domains, such as video games, recommendation systems and robotic control tasks. In continuous control tasks, widely used policies with Gaussian distributions results…
Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the…
In the field of reinforcement learning, because of the high cost and risk of policy training in the real world, policies are trained in a simulation environment and transferred to the corresponding real-world environment. However, the…