You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[GenRL] Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.
Master's thesis project on learning stateful simulations with deep differentiable models. The focus is to train a neural network to simulate a game (PONG) end-to-end.
Implementation of the paper <Model-based Reinforcement Learning for Predictions and Control for Limit Order Books (Wei et al., J.P. Morgan AI Research, 2019)>.