ml-jku / LRAM
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
☆21Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for LRAM
- Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum for Transformer Agents"☆31Updated last year
- Repo to reproduce the First-Explore paper results☆36Updated 3 weeks ago
- Generative cellular automaton-like learning environments for RL.☆19Updated last month
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆23Updated last month
- ☆13Updated 4 months ago
- Code for the paper "Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making"☆22Updated 4 months ago
- ☆15Updated 2 years ago
- JAX implementation of VQVAE/VQGAN autoencoders (+FSQ)☆19Updated 5 months ago
- A lightweight PyTorch implementation of the Transformer-XL architecture proposed by Dai et al. (2019)☆35Updated last year
- ☆17Updated 5 months ago
- speed-running solving robot manipulation tasks☆19Updated 3 weeks ago
- Reinforcement Learning inside a 3D soccer simulation☆25Updated 2 months ago
- Clean RL implementation using MLX☆27Updated 8 months ago
- Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL☆43Updated last month
- GPT implementation in Flax☆18Updated 2 years ago
- ☆29Updated 7 months ago
- We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effe…☆19Updated 9 months ago
- Jax like function transformation engine but micro, microjax☆26Updated 3 weeks ago
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆9Updated last year
- Causal Analysis of Agent Behavior for AI Safety☆17Updated last year
- PyTorch Package For Quasimetric Learning☆42Updated 3 weeks ago
- Repository for "Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics" …☆12Updated 5 months ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆39Updated 11 months ago
- ☆28Updated 3 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆36Updated last year
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆45Updated 5 months ago
- Q-Probe: A Lightweight Approach to Reward Maximization for Language Models☆37Updated 5 months ago
- ☆13Updated last week
- Galactic Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second☆82Updated last year