PyTorch implementation of DreamerV2 model-based RL algorithm

PyTorch implementation of Never Give Up: Learning Directed Exploration Strategies

A collection of offline reinforcement learning algorithms.

Reinforcement learning resources curated

Codebase for the paper "How Crucial is Transformer in Decision Transformer?". Containing experiments on different pendulum tasks and code for Decision LSTM architecture. Extension of the original D…

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

[ICLR 2024] Test-Time RL with CLIP Feedback for Vision-Language Models.

PWM: Policy Learning with Large World Models

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Online Decision Transformer

Learning Latent Dynamics for Planning from Pixels

Deep Planning Network: Control from pixels by latent planning with learned dynamics

A Simplified Pytorch Version of the Dreamer Algorithm

A pytorch implementation of Dreamer

pytorch-implementation of Dreamer (Model-based Image RL Algorithm)

Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.