understanding-search / maze-dataset

Related projects: ⓘ

• understanding-search / maze-transformer
  This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
  ☆24Updated 3 weeks ago
• quasimetric-learning / torch-quasimetric
  PyTorch Package For Quasimetric Learning
  ☆38Updated last year
• ml-jku / helm
  ☆52Updated 8 months ago
• yuqingd / cusp
  ☆15Updated 2 years ago
• yilundu / ired_code_release
  ☆39Updated 3 months ago
• ZhaolinGao / REBEL
  ☆24Updated 2 weeks ago
• astanic / crafter-ood
  ☆20Updated last year
• vivekmyers / contrastive_metrics
  Code for the paper "Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making"
  ☆20Updated 2 months ago
• abdulhaim / LMRL-Gym
  ☆65Updated 2 months ago
• ahjwang / messenger-emma
  Implements the Messenger environment and EMMA model.
  ☆22Updated last year
• facebookresearch / gen_dgrl
  Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024
  ☆26Updated last month
• kvfrans / jax-vqvae-vqgan
  JAX implementation of VQVAE/VQGAN autoencoders (+FSQ)
  ☆19Updated 3 months ago
• princeton-nlp / lwm
  We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effe…
  ☆17Updated 7 months ago
• CEC-Agent / CEC
  Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum for Transformer Agents"
  ☆30Updated 11 months ago
• aaronwalsman / ltron
  ☆56Updated 2 months ago
• UMass-Foundation-Model / COMBO
  Source codes for the paper "COMBO: Compositional World Models for Embodied Multi-Agent Cooperation"
  ☆25Updated 5 months ago
• facebookresearch / galactic
  Galactic Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second
  ☆81Updated last year
• jianlanluo / SAQ
  ☆28Updated 11 months ago
• chongyi-zheng / td_infonce
  ☆23Updated 10 months ago
• jhejna / research-lightning
  A lightweight research framework
  ☆20Updated 6 months ago
• FrankZheng2022 / PRISE
  Codebase for PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem
  ☆14Updated 2 months ago
• jbloomAus / DecisionTransformerInterpretability
  Interpreting how transformers simulate agents performing RL tasks
  ☆62Updated 10 months ago
• kvfrans / powderworld
  Code for Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
  ☆63Updated 2 weeks ago
• Stanford-ILIAD / ELLA
  Reward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.
  ☆17Updated 3 years ago
• vmicheli / delta-iris
  Efficient World Models with Context-Aware Tokenization. ICML 2024
  ☆73Updated 2 months ago
• brentyi / minGPT-flax
  GPT implementation in Flax
  ☆18Updated 2 years ago
• graliuce / sgcrl
  ☆14Updated 2 weeks ago
• chenran-li / RQL-release
  (NeurIPS 2023) Residual Q-Learning: Offline and Online Policy Customization without Value
  ☆27Updated 5 months ago
• iglu-contest / gridworld
  A reinforcement learning environment for the IGLU 2022 at NeurIPS
  ☆32Updated last year
• kvfrans / fre
  Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"
  ☆51Updated 5 months ago