Related papers: First Order Constrained Optimization in Policy Spa…

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific…

Recent RL research has utilized reward shaping--particularly complex shaping rewards such as intrinsic motivation (IM)--to encourage agent exploration in sparse-reward environments. While often effective, ``reward hacking'' can lead to the…

Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often trained with proxy rewards that only approximate the true objective, leaving them…

Policy optimization is among the most popular and successful reinforcement learning algorithms, and there is increasing interest in understanding its theoretical guarantees. In this work, we initiate the study of policy optimization for the…

We enable reinforcement learning agents to learn successful behavior policies by utilizing relevant pre-existing teacher policies. The teacher policies are introduced as objectives, in addition to the task objective, in a multi-objective…

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge. Reinforcement Learning (RL) provides a…

Offline reinforcement learning (RL) aims to optimize a policy using collected data without online interactions. Model-based approaches are particularly appealing for addressing offline RL challenges because of their capability to mitigate…

Learning agents that excel at sequential decision-making tasks must continuously resolve the problem of exploration and exploitation for optimal learning. However, such interactions with the environment online might be prohibitively…

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated…

In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint. Despite the necessary attention of the scientific community, considering stochastic stopping time, the…

In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to…

Deploying Reinforcement Learning (RL) agents in the real-world require that the agents satisfy safety constraints. Current RL agents explore the environment without considering these constraints, which can lead to damage to the hardware or…

Constrained decision-making is essential for designing safe policies in real-world control systems, yet simulated environments often fail to capture real-world adversities. We consider the problem of learning a policy that will maximize the…

Multi-turn GUI agents enable complex task completion through sequential decision-making, but suffer from severe context inflation as interaction history accumulates. Existing strategies either sacrifice long-term context via truncation or…

Many current behavior generation methods struggle to handle real-world traffic situations as they do not scale well with complexity. However, behaviors can be learned off-line using data-driven approaches. Especially, reinforcement learning…

Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of…

Reward shaping is critical in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. However, choosing effective shaping rewards from a set of reward functions in a computationally efficient…

The automatic synthesis of policies for robotic-control tasks through reinforcement learning relies on a reward signal that simultaneously captures many possibly conflicting requirements. In this paper, we in\-tro\-duce a novel,…