AlexGoldie / rl-learned-optimization
Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"
☆10Updated 2 months ago
Related projects: ⓘ
- An Open-Ended Agentic Simulator☆17Updated last month
- ☆56Updated 3 weeks ago
- ☆17Updated 3 months ago
- ☆25Updated this week
- Learning diverse options through the Laplacian representation.☆22Updated 8 months ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆51Updated 5 months ago
- Official implementation of the NeurIPS 2023 paper "Discovering General Reinforcement Learning Algorithms with Adversarial Environment Des…☆22Updated 2 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆87Updated last month
- ☆59Updated last month
- ☆11Updated 2 months ago
- Code of the paper: Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function☆13Updated last year
- Scalable Opponent Shaping Experiments in JAX☆19Updated 5 months ago
- ☆14Updated last month
- Pytorch Implementation of MuZero Unplugged for gym environment. This algorithm is capable of supporting a wide range of action and observ…☆25Updated last year
- When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)☆49Updated 8 months ago
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code☆20Updated 2 weeks ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆82Updated 9 months ago
- General Modules for JAX☆57Updated last month
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- Baselines for gymnax 🤖☆57Updated last year
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆27Updated last week
- Extreme Q-Learning: Max Entropy RL without Entropy☆78Updated last year
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆102Updated 3 weeks ago
- A collection of matrix games in JAX☆9Updated 8 months ago
- Code for the papers Hypernetworks in Meta-Reinforcement Learning (Beck et al., 2022) and Recurrent Hypernetworks are Surprisingly Strong …☆10Updated last month
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆46Updated 10 months ago
- Vectorization techniques for fast population-based training.☆52Updated 2 years ago
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆49Updated 11 months ago
- An implementation of MuZero in JAX.☆52Updated last year