Zobrazeno 1 - 10
of 2 716
pro vyhledávání: '"Safe reinforcement learning"'
Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints. However, adapting to varying safety constraints during deployment
Externí odkaz:
http://arxiv.org/abs/2412.18946
Offline safe reinforcement learning (RL) has emerged as a promising approach for learning safe behaviors without engaging in risky online interactions with the environment. Most existing methods in offline safe RL rely on cost constraints at each tim
Externí odkaz:
http://arxiv.org/abs/2412.15429
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9872-9903, 2024
A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantage-based Estimation (ABE) metho
Externí odkaz:
http://arxiv.org/abs/2412.11138
Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for practical scenarios due to its flexible transfer capability and accessi
Externí odkaz:
http://arxiv.org/abs/2412.08920
This paper addresses the target-pursuit problem, aiming to ensure each pursuer's safety regarding collision avoidance, sensing range, and input saturation. An input-constrained CBF is proposed to dynamically regulate the pursuer's control, ensuring e
Externí odkaz:
http://arxiv.org/abs/2411.17552
Real-world accidents in learning-enabled CPS frequently occur in challenging corner cases. During the training of deep reinforcement learning (DRL) policy, the standard setup for training conditions is either fixed at a single initial condition or un
Externí odkaz:
http://arxiv.org/abs/2412.13224
As large-scale distributed energy resources are integrated into the active distribution networks (ADNs), effective energy management in ADNs becomes increasingly prominent compared to traditional distribution networks. Although advanced reinforcement
Externí odkaz:
http://arxiv.org/abs/2412.01303
In this paper, we present an approach for learning collision-free robot trajectories in the presence of moving obstacles. As a first step, we train a backup policy to generate evasive movements from arbitrary initial robot states using model-free rei
Externí odkaz:
http://arxiv.org/abs/2411.05784
Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism
This paper studies the safe reinforcement learning problem formulated as an episodic finite-horizon tabular constrained Markov decision process with an unknown transition kernel and stochastic reward and cost functions. We propose a model-based algor
Externí odkaz:
http://arxiv.org/abs/2410.10158
This paper proposes a safe reinforcement learning filter (SRLF) to realize multicopter collision-free trajectory tracking with input disturbance. A novel robust control barrier function (RCBF) with its analysis techniques is introduced to avoid colli
Externí odkaz:
http://arxiv.org/abs/2410.06852