Omnisafe: An infrastructure for accelerating safe reinforcement learning research
AI systems empowered by reinforcement learning (RL) algorithms harbor the immense
potential to catalyze societal advancement, yet their deployment is often impeded by …
potential to catalyze societal advancement, yet their deployment is often impeded by …
Safety gymnasium: A unified safe reinforcement learning benchmark
Artificial intelligence (AI) systems possess significant potential to drive societal progress.
However, their deployment often faces obstacles due to substantial safety concerns. Safe …
However, their deployment often faces obstacles due to substantial safety concerns. Safe …
A review of safe reinforcement learning: Methods, theory and applications
Reinforcement learning (RL) has achieved tremendous success in many complex decision
making tasks. When it comes to deploying RL in the real world, safety concerns are usually …
making tasks. When it comes to deploying RL in the real world, safety concerns are usually …
Guard: A safe reinforcement learning benchmark
Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-
critical real-world applications, such as autonomous driving, human-robot interaction, robot …
critical real-world applications, such as autonomous driving, human-robot interaction, robot …
Towards safe reinforcement learning with a safety editor policy
We consider the safe reinforcement learning (RL) problem of maximizing utility with
extremely low constraint violation rates. Assuming no prior knowledge or pre-training of the …
extremely low constraint violation rates. Assuming no prior knowledge or pre-training of the …
Evaluating model-free reinforcement learning toward safety-critical tasks
Safety comes first in many real-world applications involving autonomous agents. Despite a
large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there …
large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there …
Conservative and adaptive penalty for model-based safe reinforcement learning
Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in
addition to maximizing a reward objective. Model-based RL algorithms hold promise for …
addition to maximizing a reward objective. Model-based RL algorithms hold promise for …
Safe dreamerv3: Safe reinforcement learning with world models
The widespread application of Reinforcement Learning (RL) in real-world situations is yet to
come to fruition, largely as a result of its failure to satisfy the essential safety demands of …
come to fruition, largely as a result of its failure to satisfy the essential safety demands of …
Datasets and benchmarks for offline safe reinforcement learning
This paper presents a comprehensive benchmarking suite tailored to offline safe
reinforcement learning (RL) challenges, aiming to foster progress in the development and …
reinforcement learning (RL) challenges, aiming to foster progress in the development and …
Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety
The safety constraints commonly used by existing safe reinforcement learning (RL) methods
are defined only on expectation of initial states, but allow each certain state to be unsafe …
are defined only on expectation of initial states, but allow each certain state to be unsafe …