valeriechen / ask-your-humans
Dataset collection and training code for "Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning"
☆9Updated 2 years ago
Related projects: ⓘ
- Reward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.☆17Updated 3 years ago
- Implements the Messenger environment and EMMA model.☆22Updated last year
- PyTorch Implementation of "Language as an Abstraction for Hierarchical Deep Reinforcement Learning" paper☆23Updated 2 years ago
- ☆35Updated 2 years ago
- Options of Interest: Temporal Abstraction with Interest Functions AAAI 2020☆25Updated 4 years ago
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆30Updated 4 years ago
- Tensorflow code for "Learning Self-Imitating Diverse Policies" (ICLR 2019)☆19Updated 3 years ago
- ☆23Updated last month
- Code for the paper Novelty Search in Representational Space for Sample Efficient Exploration presented at NeurIPS 2020.☆14Updated 2 months ago
- Codebase for "Uni[MASK]: Unified Inference in Sequential Decision Problems"☆54Updated 2 months ago
- Author's PyTorch implementation of SR-DICE for marginalized importance sampling☆15Updated 2 years ago
- ☆41Updated 5 years ago
- P3O paper code☆26Updated 5 years ago
- Latent Dynamics Mixture, NeurIPS 2021☆17Updated last year
- A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation (ICLR2023)☆11Updated last year
- Code to accompany the paper "The Information Geometry of Unsupervised Reinforcement Learning"☆21Updated 2 years ago
- ☆28Updated 2 years ago
- Official code repo for paper: Hybrid RL: Using both offline and online data can make RL efficient.☆22Updated last year
- ☆10Updated 2 years ago
- Sandbox environment for generalizable agent research☆22Updated 2 years ago
- Change-Based Exploration Transfer☆35Updated 2 years ago
- Learning Action-Value Gradients in Model-based Policy Optimization☆31Updated 3 years ago
- ☆14Updated 3 years ago
- Taming MAML: efficient unbiased meta-reinforcement learning☆28Updated last year
- Mutual Information State Intrinsic Control (ICLR 2021 Spotlight)☆36Updated 3 years ago
- CREATE Environment for long-horizon physics-puzzle tasks with diverse tools☆17Updated last year
- My Body Is A Cage☆37Updated 3 years ago
- ☆14Updated 4 years ago
- ICLR 2020 Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies☆18Updated 4 years ago
- Repository for the paper "Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors"☆44Updated last year