clvrai / leapsLinks
Code for Learning to Synthesize Programs as Interpretable and Generalizable Policies in NeurIPS 2021
☆39Updated 2 years ago
Alternatives and similar repositories for leaps
Users that are interested in leaps are comparing it to the libraries listed below
Sorting:
- ☆24Updated 3 years ago
- Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis☆38Updated 2 years ago
- Object Centric Atari games☆86Updated 2 weeks ago
- Evaluating long-term memory of reinforcement learning algorithms☆147Updated 2 years ago
- Neurosymbolic transformers for multi-agent communication.☆22Updated 4 years ago
- A public repository for "Write, Execute, Assess: Program Synthesis With a REPL" project by Kevin Ellis, Max Nye, Yewen Pu, Felix Sosa, Jo…☆38Updated 5 years ago
- Convert a PDDL domain into an OpenAI Gym environment.☆243Updated 2 weeks ago
- ☆70Updated last year
- Soft Actor-Critic☆151Updated 7 years ago
- Code for "On the Utility of Learning about Humans for Human-AI Coordination"☆109Updated 2 years ago
- Nethack Learning Environment Wrapper for Language Interface☆38Updated last year
- PAIRED in PyTorch 🔥☆62Updated 2 years ago
- Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.☆133Updated 11 months ago
- impact-driven-exploration☆131Updated last year
- ICLR'22 Programmatic Reinforcement Learning☆16Updated 2 years ago
- ☆350Updated 2 years ago
- PyTorch implementation of DreamerV2 model-based RL algorithm☆223Updated 2 years ago
- ☆235Updated 8 months ago
- ☆25Updated 3 years ago
- ☆305Updated 7 months ago
- Benchmarking RL generalization in an interpretable way.☆159Updated last month
- Deep Hierarchical Planning from Pixels☆107Updated 2 years ago
- Implementation of the Box-World environment from the paper "Relational Deep Reinforcement Learning"☆46Updated last year
- ☆18Updated 2 years ago
- PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tu…☆152Updated last year
- DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning☆22Updated 4 years ago
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.☆30Updated 4 years ago
- Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"☆161Updated 3 years ago
- Implemention of the Decision-Pretrained Transformer (DPT) from the paper Supervised Pretraining Can Learn In-Context Reinforcement Learni…☆69Updated last year
- Learning Invariant Representations for Reinforcement Learning without Reconstruction☆149Updated 3 years ago