facebookresearch / MRQ
MR.Q is a general-purpose model-free reinforcement learning algorithm.
☆91Updated 3 weeks ago
Alternatives and similar repositories for MRQ:
Users that are interested in MRQ are comparing it to the libraries listed below
- ☆82Updated 2 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆159Updated last month
- Unified Implementations of Offline Reinforcement Learning Algorithms☆64Updated last week
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆111Updated 8 months ago
- a simple and scalable agent for training adaptive policies with sequence-based RL☆119Updated last week
- Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"☆44Updated this week
- Goal-Conditioned Reinforcement Learning with JAX☆150Updated last week
- Skeleton for scalable and flexible Jax RL implementations☆80Updated last year
- Clean single-file implementation of offline RL algorithms in JAX☆143Updated 4 months ago
- ☆76Updated last month
- official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning☆92Updated 9 months ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆55Updated last year
- ☆75Updated 6 months ago
- Official implementation of the BRO algorithm☆42Updated 3 months ago
- [ICML 2024, Spotlight] EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data☆81Updated 8 months ago
- Foundation Policies with Hilbert Representations (ICML 2024)☆84Updated last year
- Transformer-based World Models☆81Updated 2 years ago
- Evaluating long-term memory of reinforcement learning algorithms☆142Updated last year
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆100Updated last year
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆66Updated 11 months ago
- ☆86Updated 11 months ago
- Extreme Q-Learning: Max Entropy RL without Entropy☆86Updated 2 years ago
- A benchmark for offline goal-conditioned RL and offline RL☆160Updated last month
- Synchronized Curriculum Learning for RL Agents☆44Updated last month
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆68Updated last year
- Synthetic Experience Replay☆93Updated 11 months ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆205Updated last month
- ☆18Updated 3 months ago
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆22Updated 2 weeks ago
- Learning diverse options through the Laplacian representation.☆23Updated last year