Related papers: Max-Entropy Reinforcement Learning with Flow Match…
While behavior cloning with flow/diffusion policies excels at learning complex skills from demonstrations, it remains vulnerable to distributional shift, and standard RL methods struggle to fine-tune these models due to their iterative…
Designing efficient algorithms for multi-agent reinforcement learning (MARL) is fundamentally challenging because the size of the joint state and action spaces grows exponentially in the number of agents. These difficulties are exacerbated…
Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement via two separate function approximators. The practicality of this approach comes at the expense of training instability, caused…
This paper explores the impact of dynamic entropy tuning in Reinforcement Learning (RL) algorithms that train a stochastic policy. Its performance is compared against algorithms that train a deterministic one. Stochastic policies optimize a…
The option framework has shown great promise by automatically extracting temporally-extended sub-tasks from a long-horizon task. Methods have been proposed for concurrently learning low-level intra-option policies and high-level option…
We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage stochastic combinatorial optimization problems from the operations research domain. In this context, risk-sensitive…
Reinforcement learning (RL) has achieved remarkable performance in numerous sequential decision making and control tasks. However, a common problem is that learned nearly optimal policy always overfits to the training environment and may…
We present GuidedSAC, a novel reinforcement learning (RL) algorithm that facilitates efficient exploration in vast state-action spaces. GuidedSAC leverages large language models (LLMs) as intelligent supervisors that provide action-level…
We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories. We propose a new way to improve the learning process by adding a…
ATARI is a suite of video games used by reinforcement learning (RL) researchers to test the effectiveness of the learning algorithm. Receiving only the raw pixels and the game score, the agent learns to develop sophisticated strategies,…
Having a perfect model to compute the optimal policy is often infeasible in reinforcement learning. It is important in high-stakes domains to quantify and manage risk induced by model uncertainties. Entropic risk measure is an exponential…
There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains…
The performance of deep reinforcement learning methods prone to degenerate when applied to environments with non-stationary dynamics. In this paper, we utilize the latent context recurrent encoders motivated by recent Meta-RL materials, and…
Safety is essential for reinforcement learning (RL) applied in real-world situations. Chance constraints are suitable to represent the safety requirements in stochastic systems. Previous chance-constrained RL methods usually have a low…
In this paper, we propose SACHER (soft actor-critic (SAC) with hindsight experience replay (HER)), which constitutes a class of deep reinforcement learning (DRL) algorithms. SAC is known as an off-policy model-free DRL algorithm based on…
Coverage Path Planning (CPP) is a fundamental capability for agricultural robots; however, existing solutions often overlook energy constraints, resulting in incomplete operations in large-scale or resource-limited environments. This paper…
This paper proposes a reinforcement learning--based framework for cryptocurrency portfolio management using the Soft Actor--Critic (SAC) and Deep Deterministic Policy Gradient (DDPG) algorithms. Traditional portfolio optimization methods…
Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particularly problematic in…
With the increasing penetration of distributed energy resources, distributed optimization algorithms have attracted significant attention for power systems applications due to their potential for superior scalability, privacy, and…
Existing imitation learning methods mainly focus on making an agent effectively mimic a demonstrated behavior, but do not address the potential contradiction between the behavior style and the objective of a task. There is a general lack of…