Egiob / cfrxLinks
cfrx is a collection of algorithms and tools for hardware-accelerated Counterfactual Regret Minimization (CFR) algorithms in Jax.
β35Updated last year
Alternatives and similar repositories for cfrx
Users that are interested in cfrx are comparing it to the libraries listed below
Sorting:
- A project that provides help for using DeepMind's mctx on gym-style environments.β61Updated 10 months ago
- Baselines for gymnax π€β71Updated 2 years ago
- Vectorization techniques for fast population-based training.β56Updated 3 years ago
- πͺ The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAXβ59Updated last year
- β83Updated 2 weeks ago
- Accelerated replay buffers in JAXβ43Updated 3 years ago
- Simple single-file baselines for Q-Learning in pure-GPU settingβ182Updated 6 months ago
- A collection of RL algorithms written in JAX.β104Updated 3 years ago
- General Modules for JAXβ67Updated 2 weeks ago
- β84Updated 10 months ago
- A collection of matrix games in JAXβ12Updated 9 months ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weightsβ¦β58Updated 3 years ago
- fast + parallel AlphaZero in JAXβ100Updated 9 months ago
- β‘ Flashbax: Accelerated Replay Buffers in JAXβ251Updated this week
- JAX implementations of core Deep RL algorithmsβ82Updated 3 years ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorchβ52Updated 2 years ago
- Scalable Opponent Shaping Experiments in JAXβ24Updated last year
- Accelerated minigrid environments with JAXβ147Updated 3 weeks ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!β236Updated 4 months ago
- Reinforcement learning in pure JAX.β13Updated 7 months ago
- Contains JAX implementation of algorithms for inverse reinforcement learningβ72Updated last year
- An implementation of MuZero in JAX.β56Updated 2 years ago
- Rainbow DQN implementation accompanying the paper "Fast and Data-Efficient Training of Rainbow" which reaches 205.7 median HNS after 10M β¦β44Updated 3 years ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]β110Updated last year
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancyβ20Updated 10 months ago
- A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each otheβ¦β161Updated 4 years ago
- Implementation of Diversity Is All You Need (DIAYN) on top of Stable Baselines 3.β12Updated 3 years ago
- Standard interface for entity based reinforcement learning environments.β38Updated last year
- Challenging Memory-based Deep Reinforcement Learning Agentsβ103Updated 10 months ago
- Classic MCTS example with mctxβ21Updated 2 years ago