相关论文: Soft Deterministic Policy Gradient with Gaussian S…

A dynamic mean field theory is developed for finite state and action Bayesian reinforcement learning in the large state space limit. In an analogy with statistical physics, the Bellman equation is studied as a disordered dynamical system;…

Domain generalization (DG) aims to learn a model using data from one or multiple related but distinct source domains that can generalize well to unseen out-of-distribution target domains. Inspired by the success of large pre-trained…

This paper deploys the Deep Deterministic Policy Gradient (DDPG) algorithm for longitudinal and lateral control of a simulated car to solve a path following task. The DDPG agent was implemented using PyTorch and trained and evaluated on a…

Changes in demand, various hydrological inputs, and environmental stressors are among the issues that water managers and policymakers face on a regular basis. These concerns have sparked interest in applying different techniques to…

Supervised approaches for text summarisation suffer from the problem of mismatch between the target labels/scores of individual sentences and the evaluation score of the final summary. Reinforcement learning can solve this problem by…

Differential Dynamic Programming (DDP) has become a well established method for unconstrained trajectory optimization. Despite its several applications in robotics and controls however, a widely successful constrained version of the…

Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, aligning dLLMs with human preferences or task-specific rewards…

Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics remain fragile. Standard algorithms like GRPO enforce stability via "hard clipping", which…

In reinforcement learning, reward shaping is an efficient way to guide the learning process of an agent, as the reward can indicate the optimal policy of the task. The potential-based reward shaping framework was proposed to guarantee…

The problem of synthesizing stochastic explicit model predictive control policies is known to be quickly intractable even for systems of modest complexity when using classical control-theoretic methods. To address this challenge, we present…

Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate of the random cumulative cost, distributional RL (DRL) seeks…

The problem of how to take the right actions to make profits in sequential process continues to be difficult due to the quick dynamics and a significant amount of uncertainty in many application scenarios. In such complicated environments,…

We introduce Group Policy Gradient (GPG), a family of critic-free policy-gradient estimators for general MDPs. Inspired by the success of GRPO's approach in Reinforcement Learning from Human Feedback (RLHF), GPG replaces a learned value…

In this paper, we present a methodology to deploy the deterministic policy gradient method, using actor-critic techniques, when the optimal policy is approximated using a parametric optimization problem, where safety is enforced via hard…

We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual…

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For $\gamma$-discounted…

Policy gradient (PG) estimation becomes a challenge when we are not allowed to sample with the target policy but only have access to a dataset generated by some unknown behavior policy. Conventional methods for off-policy PG estimation…

We present differentiable predictive control (DPC), a method for learning constrained neural control policies for linear systems with probabilistic performance guarantees. We employ automatic differentiation to obtain direct policy…

Deterministic policy gradient algorithms are foundational for actor-critic methods in controlling continuous systems, yet they often encounter inaccuracies due to their dependence on the derivative of the critic's value estimates with…