microsoft / rl-offline-simulation
Data-driven offline simulation for online reinforcement learning: benchmark and baselines
☆27Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for rl-offline-simulation
- More efficient exploration for reinforcement learning in two-player, zero-sum game☆17Updated 3 months ago
- The collection of the research works about Automatic Reinforcement Learning in Microsoft Research Asia.☆48Updated last year
- ☆30Updated 3 months ago
- INTeractive learning via REPresentatIon Discovery☆34Updated 5 months ago
- Imitation learning from multiple experts☆12Updated 2 years ago
- This repo is the official implementation of "Mask-based Latent Reconstruction for Reinforcement Learning" (NeurIPS 2022).☆26Updated last year
- ☆15Updated 3 years ago
- IV-RL - Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation☆36Updated 3 weeks ago
- A web based platform for collecting human actions in reinforcement learning environments☆27Updated last year
- Code repository accompanying the Heuristic Guided RL NeurIPS'21 paper☆12Updated 2 years ago
- ☆29Updated last year
- A lightweight reimplementation of Adversarially Trained Actor Critic☆18Updated last year
- ☆13Updated last year
- ☆33Updated 3 years ago
- ☆8Updated 2 years ago
- ☆73Updated last year
- ☆17Updated last year
- OpenAI gym environments for goal-conditioned and language-conditioned reinforcement learning☆13Updated 2 years ago
- Reinforcement Learning via Latent State Decoding☆30Updated last year
- Code for NeurIPS2023 accepted paper: Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning.☆26Updated 5 months ago
- Toolkit of Causal Model-based Reinforcement Learning.☆32Updated last year
- Sandbox environment for generalizable agent research☆23Updated 2 years ago
- Official code for "RAMBO: Robust Adversarial Model-Based Offline RL", NeurIPS 2022☆25Updated last year
- RE3: State Entropy Maximization with Random Encoders for Efficient Exploration☆67Updated 3 years ago
- Official repository for paper "Conservative Offline Distributional Reinforcement Learning" (NeurIPS 2021)☆18Updated 3 years ago
- ☆32Updated 2 months ago
- Official code for "A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning"☆14Updated last year
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆52Updated 7 months ago
- Explore and Control with Adversarial Surprise☆9Updated 3 years ago
- Benchmark data for d3rlpy☆20Updated 11 months ago