AGI-Labs / continual_rlLinks
Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.
☆123Updated 2 years ago
Alternatives and similar repositories for continual_rl
Users that are interested in continual_rl are comparing it to the libraries listed below
Sorting:
- ☆100Updated last year
- Official code repository for Prompt-DT.☆114Updated 3 years ago
- Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.☆129Updated 3 years ago
- Code for "Task-Agnostic Continual RL: In Praise of a Simple Baseline"☆34Updated 2 years ago
- Simple maze environments using mujoco-py☆57Updated last year
- ☆48Updated 2 years ago
- ☆49Updated 2 years ago
- A list of papers regarding generalization in (deep) reinforcement learning☆152Updated last year
- DMControl Generalization Benchmark☆173Updated last year
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations☆104Updated last year
- Representation Learning for RL☆126Updated 2 years ago
- ExORL: Exploratory Data for Offline Reinforcement Learning☆115Updated 3 years ago
- Pytorch version of Dreamer, which follows the original TF v2 codes.☆130Updated 3 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆100Updated 3 years ago
- Benchmarking RL generalization in an interpretable way.☆159Updated last month
- Learning to Modulate pre-trained Models in RL (Decision Transformer, LoRA, Fine-tuning)☆59Updated 10 months ago
- Deep Hierarchical Planning from Pixels☆107Updated 2 years ago
- Object Centric Atari games☆86Updated 2 weeks ago
- Generalizable Imitation Learning from Observation via Inferring Goal Proximity (NeurIPS 2021)☆23Updated 3 years ago
- ☆31Updated 2 years ago
- ☆54Updated last year
- rlplot is an easy to use and highly encapsulated RL plot library (including basic error bar lineplot and a wrapper to "rliable").☆33Updated last year
- Code for "Offline Meta-Reinforcement Learning with Advantage Weighting" [ICML 2021]☆47Updated 2 years ago
- [ICML 2022] Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning☆35Updated 2 years ago
- Official PyTorch implementation of "Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble" (NeurIPS'21)☆75Updated 2 years ago
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.☆30Updated 4 years ago
- Implementation of Multi-Game Decision Transformers in PyTorch☆47Updated 2 years ago
- off-policy RL on long sequences☆133Updated last week
- Learning Invariant Representations for Reinforcement Learning without Reconstruction☆149Updated 3 years ago
- Extreme Q-Learning: Max Entropy RL without Entropy☆87Updated 2 years ago