uoe-agents / TED
Official repository for "Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning".
☆11Updated last year
Related projects ⓘ
Alternatives and complementary repositories for TED
- Official codebase for Generating Diverse Cooperative Agents by Learning Incompatible Policies (notable-top-25% @ ICLR 2023)☆14Updated 6 months ago
- A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation (ICLR2023)☆12Updated last year
- Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning☆11Updated 6 months ago
- ☆21Updated 6 months ago
- Code for AAAI 2023 paper "Hypernetworks for Zero-shot Transfer in Reinforcement Learning"☆16Updated last year
- ☆20Updated 6 months ago
- CREATE Environment for long-horizon physics-puzzle tasks with diverse tools☆17Updated last year
- EARL: Environment for Autonomous Reinforcement Learning☆34Updated last year
- Source code for the paper "Policy Architectures for Compositional Generalization in Control"☆29Updated 2 years ago
- Lipschitz-constrained Unsupervised Skill Discovery (ICLR 2022)☆32Updated last year
- Source code to reproduce experiments from Mendez et al., ICLR '22☆20Updated 2 years ago
- Controllability-Aware Unsupervised Skill Discovery (ICML 2023)☆23Updated last year
- ☆23Updated 2 years ago
- ☆10Updated 6 months ago
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆21Updated last year
- Authors' PyTorch implementation of 'Recomposing the Reinforcement Learning Building-Blocks with Hypernetworks' (HypeRL)☆24Updated 3 years ago
- ☆13Updated 7 months ago
- Change-Based Exploration Transfer☆36Updated 2 years ago
- ☆17Updated last year
- Code to accompany the paper "The Information Geometry of Unsupervised Reinforcement Learning"☆21Updated 3 years ago
- Author's PyTorch implementation of SR-DICE for marginalized importance sampling☆15Updated 2 years ago
- Minimal Decision Transformer Implementation written in Jax (Flax).☆17Updated 2 years ago
- Jaxplorer is a Jax reinforcement learning (RL) framework for exploring new ideas.☆12Updated 3 months ago
- Codebase for the paper "How Crucial is Transformer in Decision Transformer?". Containing experiments on different pendulum tasks and code…☆24Updated last year
- Reward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.☆19Updated 3 years ago
- Code for the ICML 2023 paper "What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?".☆8Updated last year
- Model-Based Reinforcement Learning via Latent-Space Collocation.☆31Updated last year
- ☆17Updated 2 years ago
- ☆15Updated last year
- [ICLR 2024] Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.☆21Updated 6 months ago