相关论文: Mirror Descent Actor Critic via Bounded Advantage …

While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is…

Policy gradient methods in actor-critic reinforcement learning (RL) have become perhaps the most promising approaches to solving continuous optimal control problems. However, the trial-and-error nature of RL and the inherent randomness…

Most prior approaches to offline reinforcement learning (RL) utilize \textit{behavior regularization}, typically augmenting existing off-policy actor critic algorithms with a penalty measuring divergence between the policy and the offline…

We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement objective that avoids the high variance of typical policy…

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…

Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly. This idea was initially proposed in a seminal paper on…

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve over time but their…

Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is a promising paradigm for robotic manipulation, using RL to directly…

Classical on-policy algorithms such as PPO and mirror descent policy optimization provide stable proximal policy updates through tractable action likelihoods, but are typically instantiated with simple Gaussian policies whose expressiveness…

We study reinforcement learning problems where state observations are stochastically triggered by actions, a constraint common in many real-world applications. This framework is formulated as Action-Triggered Sporadically Traceable Markov…

Off-policy actor-critic methods in reinforcement learning train a critic with temporal-difference updates and use it as a learning signal for the policy (actor). This design typically achieves higher sample efficiency than purely on-policy…

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…

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages additional state information available at training time for…

Preference-conditioned multi-objective reinforcement learning aims to learn a single policy that captures trade-offs across preferences, but under nonlinear scalarization the uniqueness and continuity of the preference-to-solution…

Cross-domain Recommendation systems leverage multi-domain user interactions to improve performance, especially in sparse data or new user scenarios. However, CDR faces challenges such as effectively capturing user preferences and avoiding…

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…

We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…

Entropy Regularisation is a widely adopted technique that enhances policy optimisation performance and stability. A notable form of entropy regularisation is augmenting the objective with an entropy term, thereby simultaneously optimising…

The need for autonomous and adaptive defense mechanisms has become paramount in the rapidly evolving landscape of cyber threats. Multi-Agent Deep Reinforcement Learning (MADRL) presents a promising approach to enhancing the efficacy and…

Since the objective functions of reinforcement learning problems are typically highly nonconvex, it is desirable that policy gradient, the most popular algorithm, escapes saddle points and arrives at second-order stationary points. Existing…