Safe Reinforcement Learning

45 papers with code • 0 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?

Libraries

Use these libraries to find Safe Reinforcement Learning models and implementations
3 papers
31
3 papers
14

Most implemented papers

Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety

mahaitongdae/Feasible-Actor-Critic 22 May 2021

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, which is unsatisfying for real-world safety-critical tasks.

Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments

sisl/AutomotiveSafeRL 25 Apr 2019

Navigating urban environments represents a complex task for automated vehicles.

Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones

abalakrishna123/recovery-rl 29 Oct 2020

Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration.

MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning

metadriverse/metadrive 26 Sep 2021

Based on MetaDrive, we construct a variety of RL tasks and baselines in both single-agent and multi-agent settings, including benchmarking generalizability across unseen scenes, safe exploration, and learning multi-agent traffic.

Reachability Constrained Reinforcement Learning

mahaitongdae/Reachability_Constrained_RL 16 May 2022

Recent studies incorporate feasible sets into CRL with energy-based methods such as control barrier function (CBF), safety index (SI), and leverage prior conservative estimations of feasible sets, which harms the performance of the learned policy.

Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning

lasgroup/lbsgd-rl 21 Jul 2022

We introduce a general approach for seeking a stationary point in high dimensional non-linear stochastic optimization problems in which maintaining safety during learning is crucial.

Constrained Update Projection Approach to Safe Policy Optimization

rl-boxes/safe-rl 15 Sep 2022

Compared to previous safe RL methods, CUP enjoys the benefits of 1) CUP generalizes the surrogate functions to generalized advantage estimator (GAE), leading to strong empirical performance.

Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control

SimonRennotte/Data-Efficient-Reinforcement-Learning-with-Probabilistic-Model-Predictive-Control 20 Jun 2017

Trial-and-error based reinforcement learning (RL) has seen rapid advancements in recent times, especially with the advent of deep neural networks.

Trial without Error: Towards Safe Reinforcement Learning via Human Intervention

gsastry/human-rl 17 Jul 2017

We formalize human intervention for RL and show how to reduce the human labor required by training a supervised learner to imitate the human's intervention decisions.

Safe Reinforcement Learning via Shielding

DanielLSM/safe-rl-tutorial 29 Aug 2017

In the first one, the shield acts each time the learning agent is about to make a decision and provides a list of safe actions.