google-deepmind / constrained_optidice
☆8Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for constrained_optidice
- 🔥 Datasets and env wrappers for offline safe reinforcement learning☆76Updated 2 months ago
- Official code for "RAMBO: Robust Adversarial Model-Based Offline RL", NeurIPS 2022☆25Updated last year
- ☆52Updated last year
- ☆12Updated 2 years ago
- Offline Risk-Averse Actor-Critic (O-RAAC). A model-free RL algorithm for risk-averse RL in a fully offline setting☆33Updated 3 years ago
- Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method☆62Updated last year
- Code for the NeurIPS 2021 paper "Safe Reinforcement Learning by Imagining the Near Future"☆39Updated 2 years ago
- ☆47Updated last year
- Source files to replicate experiments in my ICLR 2022 paper.☆62Updated 4 months ago
- Safe Multi-Agent MuJoCo benchmark for safe multi-agent reinforcement learning research.☆51Updated 5 months ago
- ☆31Updated 3 years ago
- [ICML 2022] The official implementation of DWBC in "Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations"☆34Updated last year
- Code and project page for D-REX algorithm from the paper "Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrat…☆49Updated last year
- Official Codebase for TMLR 2023, Benchmarks and Algorithms for Offline Preference-Based Reward Learning☆19Updated last year
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations☆95Updated 5 months ago
- Author's PyTorch implementation of TD7 for online and offline RL☆116Updated last year
- OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation☆13Updated last year
- [ICLR 2022 Spotlight] Code for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration☆26Updated 2 years ago
- Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning☆23Updated last year
- Implementations of SAILR, PDO, and CSC☆31Updated 4 months ago
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆62Updated last year
- ☆28Updated last year
- ☆40Updated 3 years ago
- Official repository for paper "Conservative Offline Distributional Reinforcement Learning" (NeurIPS 2021)☆18Updated 3 years ago
- Benchmarked implementations of Offline RL Algorithms.☆65Updated 6 months ago
- CORRO code☆34Updated 2 years ago
- ☆30Updated 3 months ago
- A novel Hierarchical Imitation Learning algorithm based on AIRL.☆19Updated last year
- Inverse Reinforcement Learning via State Marginal Matching, CoRL 2020☆42Updated last year
- Simple maze environments using mujoco-py☆52Updated 10 months ago