nuria95 / O-RAAC
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
Related projects ⓘ
Alternatives and complementary repositories for O-RAAC
- Code for the NeurIPS 2021 paper "Safe Reinforcement Learning by Imagining the Near Future"☆39Updated 2 years ago
- Code for Latent Action Space for Offline Reinforcement Learning [CoRL 2020]☆49Updated 3 years ago
- ☆52Updated last year
- [ICML 2022] The official implementation of DWBC in "Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations"☆34Updated last year
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆62Updated last year
- Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning☆28Updated 2 years ago
- Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method☆62Updated last year
- [ICLR 2022 Spotlight] Code for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration☆26Updated 2 years ago
- We investigate the effect of populations on finding good solutions to the robust MDP☆28Updated 3 years ago
- ☆31Updated 3 years ago
- When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)☆55Updated 10 months ago
- ☆54Updated 8 months ago
- Implementation of ICML2020 paper <Bidirectional Model-based Policy Optimization>☆23Updated last year
- Model-Based Offline Reinforcement Learning☆47Updated 3 years ago
- Code accompanying the paper "Action Robust Reinforcement Learning and Applications in Continuous Control" https://arxiv.org/abs/1901.0918…☆41Updated 5 years ago
- Unofficial PyTorch implementation (replicating paper results) of Implicit Q-Learning (In-sample Q-Learning) for offline RL☆22Updated 3 weeks ago
- Implementations of SAILR, PDO, and CSC☆31Updated 4 months ago
- Simple maze environments using mujoco-py☆52Updated 10 months ago
- ☆40Updated 3 years ago
- Safe Multi-Agent MuJoCo benchmark for safe multi-agent reinforcement learning research.☆51Updated 5 months ago
- Official code for "RAMBO: Robust Adversarial Model-Based Offline RL", NeurIPS 2022☆25Updated last year
- Benchmarked implementations of Offline RL Algorithms.☆65Updated 6 months ago
- DecentralizedLearning☆21Updated last year
- Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination☆25Updated last year
- LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization☆32Updated last year
- Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning☆23Updated last year
- on-policy optimization baselines for deep reinforcement learning☆28Updated 4 years ago
- The official repository of Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration" (AAMAS 2022)☆26Updated 2 years ago
- Generalized Decision Transformer for Offline Hindsight Information Matching (ICLR2022)☆66Updated 2 years ago
- Code for MOBILE: Model-Bellman Inconsistency Penalized Offline Policy Optimization☆15Updated 7 months ago