"polyak averaging"https://spinningup.openai.com/en/latest/algorithms/sac.html#:~:text=are%20obtained%20by-,polyak%20averaging,-the%20Q-network
Level up in AI
Asynchronous Methods for Deep Reinforcement Learning
1602.01783.pdf
Finish reading Spinning up in Deep RL
Add Proof for Using Q-Function in Policy Gradient Formula into Anki
Add this expected grad-log-prob lemma card to Anki
Add derivation of trajectory return policy gradient to Anki
Do Deep RL course on Berkeley
Do Deep RL Bootcamp
Learning Tetris Using the Noisy Cross-Entropy Method
neco.2006.18.12.2936.pdf
Opportunities
Microsoft AI residency
Learn DDPG
Continuous control with deep reinforcement learning
1509.02971.pdf
Learn PPO
Proximal Policy Optimization Algorithms
1707.06347.pdf
Learn conjugate gradient algorithm
Learn QR-DQN
Distributional Reinforcement Learning with Quantile Regression
1710.10044.pdf
Learn Twin Delayed DDPG
Implement TD(lambda)
Learn batch norm, layer norm, weight norm
Learn C51
A Distributional Perspective on Reinforcement Learning
1707.06887.pdf
Learn SVG
Learning Continuous Control Policies by Stochastic Value Gradients
1510.09142.pdf
Learn MBMF
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning
1708.02596.pdf
Read thesis with TRPO
Learn natural policy gradient methods
A Natural Policy Gradient
NIPS-2001-a-natural-policy-gradient-Paper.pdf
Learn Soft Actor-Critic
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
1801.01290.pdf
Read and Ankify Algorithms for reinforcement learning 2009 lecture
Ankify Nuts and bolts of deep RL research
Learn and understand deep belief network per-layer (pre)training
Why does L1 penalty encourage sparsity?
Learn more about energy models
AI safety materials at UMass
Level up in AI resources
Language Modelling at Scale: Gopher, Ethical considerations, and Retrieval
Relative reachability code
RL Unplugged benchmark
minGPT: a small and educational implementation of GPT by Andrej Karpathy
NeurIPS proceedings
OpenAI Safety Gym
Progress on Causal Influence Diagrams
Bayesian Optimization
bayesoptbook.pdf
A Preliminary Exploration into Factored Cognition with Language Models | EleutherAI
Advancing mathematics by guiding human intuition with AI | Nature
RLDS: An Ecosystem to Generate, Share, and Use Datasets in Reinforcement Learning
R2D2 - Recurrent Experience Replay in Distributed Reinforcement Learning
R2D3 - R2D2 from Demonstrations
DeepMind Reinforcement Learning Lecture Series 2021
CLIP model
deepmind/alphafold: Open source code for AlphaFold.
TensorFlow vs PyTorch
Colab notebook - creates image from text using SIREN and CLIP
xg2xg
6 Month Study Guide For ML Interviews
GitHub - google/model_search
How We Won The NeurIPS 2020 Black Box Optimisation Competition
ML-Agents Playlist on YouTube (Unity / Reinforcement Learning)
Minimal implementations of deep learning pape
MIT's "deep learning boot camp"
Cosine annealed warm restart learning schedule
CMU, Google & UC Berkeley Propose Robust Predictable Control Policies for RL Agents
"torch-imle": PyTorch library for transforming any combinatorial black-box solver in differentiable layer (pathing, maze-solving, integer programming, Markov Logic Networks)
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
2106.01798.pdf
2-D Robustness
Facebook Salina
ML Collective
SafeLife
Thread: Circuits
DERL
faster transformer
contains Anki cards for VAEs, transformers, MLP-mixers
Graph Neural Networks through the lens of Differential Geometry and Algebraic Topology
NeurIPS 2021 papers
Top TensorFlow-Based Projects That ML Beginners Should Try
ML & deep learning compendium open book
Transformers code
What's Polyak averaging?
Value Dice
Perceiver implementation
Tandem DQN
Transformers from Scratch
char-rnn
Learn contraction mapping proof of Q learning stuff
Minorization-maximization algorithms
Awesome metric learning
AIXIjs
PyTorch vs TensorFlow in 2022
AGI Safety Talks at EA Cambridge
Stanford's ML with graphs course
CHAI weekly seminars
Understand MuZero
HuggingFace course
There's a few ways to write the value of a policy and i can't prove they have the same gradient
Get TensorFlow developer certificate
AGI Safety Fundamentals course
How to do RL on a POMDP?
Learn how a k-d tree works
"ML algorithms cheat sheet"