microsoft / rl-offline-simulationLinks
Data-driven offline simulation for online reinforcement learning: benchmark and baselines
☆30Updated last year
Alternatives and similar repositories for rl-offline-simulation
Users that are interested in rl-offline-simulation are comparing it to the libraries listed below
Sorting:
- Imitation learning from multiple experts☆12Updated 3 years ago
- The collection of the research works about Automatic Reinforcement Learning in Microsoft Research Asia.☆58Updated 2 months ago
- INTeractive learning via REPresentatIon Discovery☆34Updated last year
- This repo is the implementation of paper ''SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning''.☆49Updated last year
- Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories☆43Updated 2 years ago
- ☆32Updated last year
- Repo for ICML'23 paper SurCo Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems☆18Updated 2 years ago
- Code repository accompanying the Heuristic Guided RL NeurIPS'21 paper☆15Updated 3 years ago
- This repo is the official implementation of "Mask-based Latent Reconstruction for Reinforcement Learning" (NeurIPS 2022).☆28Updated 2 years ago
- TaskMet Task-driven Metric Learning for Model Learning☆19Updated last year
- ☆10Updated 3 years ago
- GBRL-based Actor-Critic algorithms implemented in stable-baselines3☆38Updated 2 months ago
- Experiment for Understanding the Effects of Dataset Characteristics on Offline Reinforcement Learning☆25Updated 2 years ago
- IV-RL - Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation☆40Updated 2 months ago
- Explore and Control with Adversarial Surprise☆10Updated 4 years ago
- This is the pytorch implementation of the UAI2023 paper "A Trajectory is Worth Three Sentences: Multimodal Transformer for Offline Reinf…☆11Updated 2 years ago
- A web based platform for collecting human actions in reinforcement learning environments☆30Updated last month
- Toolkit of Causal Model-based Reinforcement Learning.☆32Updated 2 years ago
- ☆54Updated 2 years ago
- MARS is shortened for Multi-Agent Research Studio, a library for mulit-agent reinforcement learning research.☆48Updated last year
- More efficient exploration for reinforcement learning in two-player, zero-sum game☆21Updated last year
- Contains implementation of the FILTER algorithm for exponentially faster inverse reinforcement learning.☆51Updated 2 years ago
- Pytorch code for "Learning Guidance Rewards with Trajectory-space Smoothing" (NeurIPS 2020)☆12Updated 4 years ago
- PyTorch implementation for "On the Critical Role of Conventions in Adaptive Human-AI Collaboration", ICLR 2021☆16Updated 4 years ago
- Logarithmic Reinforcement Learning☆26Updated 2 years ago
- ☆54Updated 3 years ago
- Implementations of a large collection of reinforcement learning algorithms.☆28Updated last year
- Codebase for ICLR 2023 paper, "SMART: Self-supervised Multi-task pretrAining with contRol Transformers"☆54Updated last year
- Understanding RL vision Distill article☆24Updated 2 years ago
- An unofficial implementation for online decision transformer☆40Updated 3 years ago