research
∙
07/27/2023
Thinker: Learning to Plan and Act
We propose the Thinker algorithm, a novel approach that enables reinforc...
share
research
∙
07/25/2023
Unbiased Weight Maximization
A biologically plausible method for training an Artificial Neural Networ...
research
∙
07/25/2023
Structural Credit Assignment with Coordinated Exploration
A biologically plausible method for training an Artificial Neural Networ...
research
∙
11/27/2022
Domain Generalization for Robust Model-Based Offline Reinforcement Learning
Existing offline reinforcement learning (RL) algorithms typically assume...
research
∙
10/19/2020
Every Hidden Unit Maximizing Output Weights Maximizes The Global Reward
For a network of stochastic units trained on a reinforcement learning ta...
research
∙
10/15/2020
An Alternative to Backpropagation in Deep Reinforcement Learning
State-of-the-art deep learning algorithms mostly rely on gradient backpr...
research
∙
08/29/2020