相关论文: Tactical Optimism and Pessimism for Deep Reinforce…

Deep off-policy actor-critic algorithms have emerged as the leading framework for reinforcement learning in continuous control domains. However, most of these algorithms suffer from poor sample efficiency, especially in environments with…

Reinforcement Learning (RL) has been able to solve hard problems such as playing Atari games or solving the game of Go, with a unified approach. Yet modern deep RL approaches are still not widely used in real-world applications. One reason…

Model-based algorithms, which learn a dynamics model from logged experience and perform some sort of pessimistic planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (offline RL).…

Actor-critic (AC) algorithms are known for their efficacy and high performance in solving reinforcement learning problems, but they also suffer from low sampling efficiency. An AC based policy optimization process is iterative and needs to…

By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include…

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the…

Linear dynamical systems that obey stochastic differential equations are canonical models. While optimal control of known systems has a rich literature, the problem is technically hard under model uncertainty and there are hardly any…

There are many algorithms for regret minimisation in episodic reinforcement learning. This problem is well-understood from a theoretical perspective, providing that the sequences of states, actions and rewards associated with each episode…

In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update…

The main challenge for adaptive regulation of linear-quadratic systems is the trade-off between identification and control. An adaptive policy needs to address both the estimation of unknown dynamics parameters (exploration), as well as the…

We focus on a simulation-based optimization problem of choosing the best design from the feasible space. Although the simulation model can be queried with finite samples, its internal processing rule cannot be utilized in the optimization…

Dynamic mechanism design has garnered significant attention from both computer scientists and economists in recent years. By allowing agents to interact with the seller over multiple rounds, where agents' reward functions may change with…

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Recent successful deep reinforcement learning algorithms, such as Trust Region Policy Optimization (TRPO) or Proximal Policy Optimization (PPO), are fundamentally variations of conservative policy iteration (CPI). These algorithms iterate…

Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain…

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…

Pessimism is of great importance in offline reinforcement learning (RL). One broad category of offline RL algorithms fulfills pessimism by explicit or implicit behavior regularization. However, most of them only consider policy divergence…

Online reinforcement learning (RL) with complex function approximations such as transformers and deep neural networks plays a significant role in the modern practice of artificial intelligence. Despite its popularity and importance,…

Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning control strategies from raw image pixels. However,…

Robotic manipulation remains challenging for reinforcement learning due to contact-rich dynamics, long horizons, and training instability. Although off-policy actor-critic algorithms such as SAC and TD3 perform well in simulation, they…