I forked Open AI's baseline code and made a few changes. This was my first full run before I started playing around with the model architecture.
Changes from OpenAI's: * Turned on Logging, including Tensorboard output * Log rewards * Add a command line option for setting number of cpus
Code: Commit used …
read moreA long review of the use of DL in robotics
read moreA long review of the use of DL in robotics
read moreNotes on using Eligibility Traces with neural networks
read moreA single ML model used for very different tasks.
read moreRelationships between objects.
read moreFive questions to ask about your deep learning project.
read moreIncrease speed of a Reinforcement Learning system with auxiliary task.
read moreOverview (with references) of attention and several types of augmentation for RNNs.
read moreIn-progress second edition of an RL textbook.
read moreImproved Q-value estimation by reducing overestimates of Deep Q-networks.
read moreOne of the first deep reinforcement learning papers.
read moreOff-Policy AC with linear state features. Includes elegibility traces.
read moreMaLPi (Machine Learning Pi)
First, the hardware. This is my current setup and although I've tested each piece separately, I haven't had them all working together, yet.
Using RL value functions to encode semantic knowledge, specifically by a robot.
read more