czp16 / FCSRLLinks
Feasibility Consistent Representation Learning for Safe Reinforcement Learning (ICML 2024). Current SOTA model-free safe RL algorithm on safety-gymnasium
☆10Updated last year
Alternatives and similar repositories for FCSRL
Users that are interested in FCSRL are comparing it to the libraries listed below
Sorting:
- ☆54Updated 7 months ago
- This is the source code of FUSION, a safety-aware causal representation for generalizable driving agents.☆21Updated 10 months ago
- SocialGym 2: A lightweight benchmark and simulator for multi-robot social navigation using ROS and the OpenAI gym.☆61Updated last year
- Implementation of Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones.☆59Updated 2 years ago
- Official open-source implementation of ICML 2022 paper: Reachability Constrainted Reinforcement Learning.☆36Updated 3 years ago
- ☆16Updated last year
- [ICLR 2025] Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning.☆65Updated last month
- Code release for the paper "Towards Safe Reinforcement Learning with a Safety Editor Policy", Yu et al., arXiv 2022☆15Updated 5 months ago
- 🔥 Datasets and env wrappers for offline safe reinforcement learning☆103Updated last year
- Code for the NeurIPS 2021 paper "Safe Reinforcement Learning by Imagining the Near Future"☆46Updated 3 years ago
- ICLR 2024: SafeDreamer: Safe Reinforcement Learning with World Models☆78Updated last year
- Official implementation of the paper: Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate☆24Updated last year
- [ICML'2023 Oral] "AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners"☆64Updated last year
- This is the code repository accompanying the ICML 2021 paper LTL2Action: Generalizing LTL Instructions for Multi-Task RL (https://arxiv.o…☆33Updated last year
- [IROS 22'] Model-free Neural Lyapunov Control☆24Updated 2 years ago
- [ICLR 2024] The official implementation of "Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model"☆108Updated 7 months ago
- Code for Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations☆18Updated 3 years ago
- [NeurIPS 2023] Implementation of Elastic Decision Transformer☆35Updated last year
- This is the official implementation of NeurIPS 2022 paper "Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal R…☆34Updated 2 years ago
- Code for L4DC 2022 paper: Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning.☆15Updated 2 years ago
- 🔥Systematic Benchmarking of Neural Network Architectures in Reinforcement Learning.☆23Updated 3 months ago
- Control Synthesis from Formal Specifications using Reinforcement Learning☆24Updated last month
- This repository has code for the paper "Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algor…☆28Updated 2 years ago
- ☆20Updated last year
- Implementations of safe reinforcement learning algorithms☆28Updated last year
- Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"☆31Updated 4 years ago
- ☆72Updated last year
- (NeurIPS 2023) Residual Q-Learning: Offline and Online Policy Customization without Value☆34Updated last year
- [NeurIPS 2023] Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans☆21Updated last year
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆70Updated 2 years ago