jlin816 / rewards-from-language
Code and data for "Inferring Rewards from Language in Context" [ACL 2022].
☆15Updated 2 years ago
Related projects: ⓘ
- Implements the Messenger environment and EMMA model.☆22Updated last year
- [ICLR 2022 Spotlight] Multi-Stage Episodic Control for Strategic Exploration in Text Games☆13Updated 2 years ago
- Code for LaMPP: Language Models as Probabilistic Priors for Perception and Action☆35Updated last year
- ☆19Updated 2 years ago
- A visual semantic planner for the ALFRED virtual agent challenge using the GPT-2 language model☆14Updated 3 years ago
- Reward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.☆17Updated 3 years ago
- ☆12Updated 3 years ago
- ☆23Updated last year
- Official code for our EMNLP2021 Outstanding Paper MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks☆19Updated last year
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆35Updated 8 months ago
- ☆35Updated 2 months ago
- Official code for the ACL 2021 Findings paper "Yichi Zhang and Joyce Chai. Hierarchical Task Learning from Language Instructions with Uni…☆24Updated 3 years ago
- ☆75Updated last month
- ☆25Updated last year
- Code used to run experiments for the ICLR 2023 paper "Computational Language Acquisition with Theory of Mind".☆14Updated last year
- Grounded SCAN data set.☆69Updated 2 years ago
- Dataset collection and training code for "Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning"☆9Updated 2 years ago
- The multi-modal sequence to sequence baseline neural models used in the Grounded SCAN paper.☆16Updated 3 years ago
- Code accompanying ICML 2021 paper "Few-shot Language Coordination by Modeling Theory of Mind"☆18Updated 2 years ago
- ☆25Updated 9 months ago
- ReaSCAN is a synthetic navigation task that requires models to reason about surroundings over syntactically difficult languages. (NeurIPS…☆19Updated 2 years ago
- ☆28Updated 5 months ago
- Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]☆116Updated 2 years ago
- [ICLR 2022] Linking Emergent and Natural Languages via Corpus Transfer☆30Updated 3 months ago
- Instruction Following Agents with Multimodal Transforemrs☆50Updated last year
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆23Updated 9 months ago
- Repository for DialFRED.☆40Updated last year
- ☆12Updated 8 months ago
- Code for EmBERT, a transformer model for embodied, language-guided visual task completion.☆57Updated 5 months ago
- A reinforcement learning environment for the IGLU 2022 at NeurIPS☆32Updated last year