Reinforcement Learning

I

Sutton & Barto, Reinforcement Learning: An Introduction (2nd ed.) — full-book PDF PDF 9 terms

+1 more

P

Monte Carlo Methods — CSCI-531: every-visit MC prediction contrasted with first-visit Art… 4 terms

A

Concrete Problems in AI Safety Pap… 3 terms

S

OpenAI Spinning Up — Part 3: Intro to Policy Optimization (Baselines in Policy Gradients) Art… 3 terms

O

Reinforcement Learning — Monte Carlo Methods: every-visit vs first-visit estimators and convergence Art… 3 terms

S

Reward and Return: discounted return and why future rewards are discounted by γ — OpenAI Spinning Up Art… 3 terms

W

Sutton & Barto, Chapter 4: Dynamic Programming — slides defining Generalized Policy Iteration PDF 3 terms

H

The Reinforcement Learning Framework: the agent-environment loop — Hugging Face Deep RL Course Docs 3 terms

P

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning (DAgger) Pap… 2 terms

A

Asynchronous Methods for Deep Reinforcement Learning (A3C paper) Pap… 2 terms

A

Continuous control with deep reinforcement learning (DDPG) Pap… 2 terms

G

Gymnasium Environment API documentation Docs 2 terms

A

High-Dimensional Continuous Control Using Generalized Advantage Estimation Pap… 2 terms

N

Human-level control through deep reinforcement learning (DQN) Pap… 2 terms

I

Markov Decision Processes: finite-horizon and infinite-horizon value functions — MIT 6.390 notes Art… 2 terms

A

MuZero: Mastering Atari, Go, chess and shogi by planning with a learned model Pap… 2 terms

N

Nature: Mastering the game of Go with deep neural networks and tree search Pap… 2 terms

A

Playing Atari with Deep Reinforcement Learning (original DQN paper) Pap… 2 terms

A

Prioritized Experience Replay Pap… 2 terms

A

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning Pap… 2 terms

A

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (Bubeck and Cesa-Bianchi) Pap… 2 terms

A

9.5.2 Value Iteration — Artificial Intelligence: Foundations of Computational Agents (2nd ed.) Art… 1 term

A

9.5.3 Policy Iteration — Artificial Intelligence: Foundations of Computational Agents (2nd ed.) Art… 1 term

A

A Contextual-Bandit Approach to Personalized News Article Recommendation (Li, Chu, Langford, Schapire - LinUCB) Pap… 1 term

A

A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem Pap… 1 term

A

A Distributional Perspective on Reinforcement Learning (C51) Pap… 1 term

A

A Survey and Critique of Multiagent Deep Reinforcement Learning Pap… 1 term

I

A Survey of Monte Carlo Tree Search Methods Pap… 1 term

A

A Survey of Temporal Credit Assignment in Deep Reinforcement Learning (Pignatelli et al., 2023) Pap… 1 term

A

A Tutorial on Thompson Sampling Pap… 1 term

A

Addressing Function Approximation Error in Actor-Critic Methods (the TD3 paper) Pap… 1 term

J

Adversarial Bandits and the EXP3 Algorithm (Math n Programming) Art… 1 term

A

Algorithms for Inverse Reinforcement Learning (Ng & Russell, ICML 2000) PDF 1 term

A

An Algorithmic Perspective on Imitation Learning Pap… 1 term

A

Arcade Learning Environment documentation Art… 1 term

T

Bandit Algorithms by Lattimore and Szepesvari (free online edition) PDF 1 term

E

Bellman equation — Wikipedia (principle of optimality and the Bellman optimality equation) Ref… 1 term

L

Bellman Optimality Equations for V* and Q* — Lil'Log, A (Long) Peek into Reinforcement Learning Art… 1 term

A

Breaking the Deadly Triad with a Target Network (Zhang, Yao & Whiteson, ICML 2021) Pap… 1 term

A

Conservative Q-Learning for Offline Reinforcement Learning Pap… 1 term

V

Contextual Bandits - Vowpal Wabbit official documentation and tutorial Docs 1 term

A

Curiosity-driven Exploration by Self-supervised Prediction Pap… 1 term

A

Deep Radial-Basis Value Functions for Continuous Control (Asadi, Parikh, Parr, Konidaris & Littman) Pap… 1 term

A

Deep Reinforcement Learning and the Deadly Triad (van Hasselt et al., DeepMind) Pap… 1 term

A

Deep Reinforcement Learning for Autonomous Driving: A Survey Pap… 1 term

A

Deep reinforcement learning from human preferences Pap… 1 term

A

Deep Reinforcement Learning with Double Q-learning (van Hasselt et al. — the Double DQN paper) Pap… 1 term

A

DeepMind Lab (original paper, arXiv:1612.03801) Pap… 1 term

G

DeepMind Lab official source repository Code 1 term

D

DeepMind: AlphaZero — Shedding new light on chess, shogi, and Go Art… 1 term

P

Deterministic Policy Gradient Algorithms — Silver et al. (ICML 2014) Pap… 1 term

A

Distributional Reinforcement Learning with Quantile Regression (QR-DQN) Pap… 1 term

P

Double Q-learning paper from NeurIPS 2010 Art… 1 term

A

DreamerV3: Mastering Diverse Domains through World Models Pap… 1 term

A

Dueling Network Architectures for Deep Reinforcement Learning Pap… 1 term

P

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables (PEARL) Pap… 1 term

A

Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning Pap… 1 term

P

Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments (Seldin, Szepesvari, Auer, Abbasi-Yadkori) Pap… 1 term

A

Exploration by Random Network Distillation Pap… 1 term

H

Finite-time Analysis of the Multiarmed Bandit Problem (Auer, Cesa-Bianchi, Fischer, 2002) - the UCB1 paper PDF 1 term

P

Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding (Sutton, NIPS 1995) — the CMAC/tile-coding paper Art… 1 term

P

Generative Adversarial Imitation Learning (NeurIPS 2016) Art… 1 term

G

Google Research RecSim: simulation for recommendation policies Code 1 term

G

Gymnasium documentation Art… 1 term

G

Gymnasium documentation: Spaces Docs 1 term

G

Gymnasium MuJoCo environments Art… 1 term

G

Handling Time Limits — Gymnasium Documentation (termination vs truncation) Art… 1 term

A

Hindsight Credit Assignment (Harutyunyan et al., NeurIPS 2019) Pap… 1 term

A

Hindsight Experience Replay paper Pap… 1 term

A

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Pap… 1 term

S

Key Concepts and Terminology: agents, environments and the interaction loop — OpenAI Spinning Up Art… 1 term

E

Lai-Robbins lower bound: the logarithmic regret bound for stochastic bandits Ref… 1 term

P

Lecture 3: Stochastic Bandits (Akshay Krishnamurthy) PDF 1 term

R

Lecture 7: Function Approximation — RL Theory (linear value function approximation with basis functions) Art… 1 term

P

Leveraging Procedural Generation to Benchmark Reinforcement Learning (Procgen Benchmark, ICML 2020) Pap… 1 term

A

MADDPG: Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments Pap… 1 term

A

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (AlphaZero) Pap… 1 term

N

Mastering the game of Go without human knowledge (AlphaGo Zero) Pap… 1 term

C

Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy (Ziebart PhD thesis) PDF 1 term

A

Monte Carlo Method for Learning State-Value Functions — First-Visit Method (tutorial with Python) Art… 1 term

M

MuJoCo documentation — Overview Docs 1 term

N

Nature paper: Mastering Atari, Go, chess and shogi by planning with a learned model Pap… 1 term

A

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems Pap… 1 term

G

OpenAI Gym archived repository Code 1 term

S

OpenAI Spinning Up — Part 2: Kinds of RL Algorithms (model-free vs model-based) Art… 1 term

S

OpenAI Spinning Up — Part 3: Intro to Policy Optimization Art… 1 term

S

OpenAI Spinning Up: Deep Deterministic Policy Gradient Art… 1 term

S

OpenAI Spinning Up: Soft Actor-Critic Art… 1 term

S

OpenAI Spinning Up: Trust Region Policy Optimization Art… 1 term

S

OpenAI Spinning Up: Twin Delayed DDPG (TD3) Art… 1 term

L

Optimal Value and Policy: V*, Q* and the optimal policy π* — Lil'Log, A (Long) Peek into RL Art… 1 term

J

Optimism in the Face of Uncertainty: the UCB1 Algorithm (Math n Programming) Art… 1 term

S

Policies: deterministic, stochastic and parameterized — OpenAI Spinning Up, Key Concepts in RL Art… 1 term

G

Policy Iteration — Mastering Reinforcement Learning (Tim Miller) Art… 1 term

A

Proximal Policy Optimization Algorithms — Schulman et al. Pap… 1 term

G

Q-function approximation — Mastering Reinforcement Learning (Tim Miller) Art… 1 term

A

Quantifying Generalization in Reinforcement Learning (Cobbe et al., 2018) Pap… 1 term

A

Rainbow: Combining Improvements in Deep Reinforcement Learning Pap… 1 term

A

Reinforcement Learning with Function Approximation: From Linear to Nonlinear (Long & Han) Pap… 1 term

T

Reinforcement Learning, Part 7: Introduction to Value-Function Approximation Art… 1 term

T

Reinforcement Learning, Part 8: Feature State Construction (polynomial, Fourier, aggregation, coarse/tile coding, RBFs) Art… 1 term

W

Reinforcement Learning: An Introduction, Chapter 3 on Finite Markov Decision Processes PDF 1 term

A

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents Pap… 1 term

A

RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning Pap… 1 term

D

RLlib algorithm guide Docs 1 term

D

RLlib documentation Docs 1 term

L

Simple statistical gradient-following algorithms for connectionist reinforcement learning (Williams 1992 — the REINFORCE paper) Pap… 1 term

A

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor Pap… 1 term

D

Specification gaming: the flip side of AI ingenuity Art… 1 term

D

Specification gaming: the flip side of AI ingenuity — Google DeepMind (reward misspecification) Art… 1 term

S

Stable Baselines3 documentation Docs 1 term

G

Stable Baselines3 GitHub repository Code 1 term

S

Stable Baselines3 — A2C (Advantage Actor Critic) documentation Docs 1 term

S

Stable Baselines3 — PPO documentation Docs 1 term

E

State-action-reward-state-action (SARSA) — Wikipedia Ref… 1 term

S

States and Observations: full vs partial descriptions of the world — OpenAI Spinning Up Art… 1 term

S

Stochastic Multi-Armed Bandit Problem and Algorithms (Oxford, Algorithmic Foundations of Learning, Lecture 15) PDF 1 term

G

Temporal difference reinforcement learning — SARSA (on-policy) compared with Q-learning Art… 1 term

L

The Multi-Armed Bandit Problem and Its Solutions (Lilian Weng) Art… 1 term

C

The Non-stochastic Multi-armed Bandit Problem (Auer, Cesa-Bianchi, Freund, Schapire) PDF 1 term

A

The Option-Critic Architecture Pap… 1 term

H

The Policy π: the brain of the agent — Hugging Face Deep RL Course Docs 1 term

A

The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games (MAPPO) Pap… 1 term

M

Tile Coding — RL Sketchpad: offset tilings, binary features and gradient Monte Carlo approximation Art… 1 term

A

Training language models to follow instructions with human feedback (InstructGPT) Pap… 1 term

S

Trajectories (τ = s0, a0, s1, a1, …) — OpenAI Spinning Up, Key Concepts in RL Art… 1 term

J

Transfer Learning for Reinforcement Learning Domains: A Survey Pap… 1 term

A

Trust Region Policy Optimization — Schulman et al. Pap… 1 term

G

Unity ML-Agents GitHub Repository Code 1 term

G

Value Iteration — Mastering Reinforcement Learning (Tim Miller) Art… 1 term

A

World Models — Ha & Schmidhuber (original paper) Pap… 1 term