Reinforcement Learning

107 methods • 6505 papers with code

Policy Gradient Methods

PPO

629 papers with code

DDPG

190 papers with code

REINFORCE

160 papers with code

TD3

90 papers with code

TRPO

71 papers with code

See all 24 methods

Off-Policy TD Control

Q-Learning

1427 papers with code

DQN

441 papers with code

Double Q-learning

106 papers with code

Clipped Double Q-learning

95 papers with code

Double DQN

42 papers with code

See all 16 methods

Reinforcement Learning Frameworks

AM

198 papers with code

SCST

11 papers with code

POMO

4 papers with code

DDQL

3 papers with code

Sym-NCO

2 papers with code

See all 11 methods

Q-Learning Networks

DQN

441 papers with code

Double DQN

42 papers with code

REM

37 papers with code

Dueling Network

22 papers with code

Rainbow DQN

8 papers with code

See all 10 methods

Heuristic Search Algorithms

GA

200 papers with code

Monte-Carlo Tree Search

138 papers with code

Firefly algorithm

16 papers with code

4D A*

1 papers with code

IGSA

1 papers with code

See all 8 methods

Value Function Estimation

HOC

341 papers with code

V-trace

32 papers with code

Retrace

27 papers with code

N-step Returns

25 papers with code

Stochastic Dueling Network

11 papers with code

See all 7 methods

Distributed Reinforcement Learning

IMPALA

15 papers with code

Ape-X

10 papers with code

DD-PPO

7 papers with code

APPO

2 papers with code

SEED RL

2 papers with code

See all 7 methods

On-Policy TD Control

Sarsa

46 papers with code

TD Lambda

12 papers with code

Expected Sarsa

7 papers with code

True Online TD Lambda

Sarsa Lambda

See all 5 methods

Imitation Learning Methods

Parrot

7 papers with code

PWIL

3 papers with code

IQ-Learn

3 papers with code

CLIPort

2 papers with code

b2b transfer learning

1 papers with code

See all 5 methods

Board Game Models

AlphaZero

88 papers with code

MuZero

36 papers with code

TD-Gammon

2 papers with code

See all 4 methods

Eligibility Traces

Accumulating Eligibility Trace

13 papers with code

Eligibility Trace

10 papers with code

Dutch Eligibility Trace

Replacing Eligibility Trace

See all 4 methods

Behaviour Policies

Go-Explore

15 papers with code

Epsilon Greedy Exploration

4 papers with code

See all 4 methods

Offline Reinforcement Learning Methods

R2D2

17 papers with code

IQL

10 papers with code

Fisher-BRC

1 papers with code

See all 3 methods

Replay Memory

Experience Replay

723 papers with code

Prioritized Experience Replay

115 papers with code

See all 2 methods

Efficient Planning

Prioritized Sweeping

5 papers with code

See all 2 methods

Randomized Value Functions

REM

37 papers with code

Noisy Linear Layer

10 papers with code

See all 2 methods

Video Game Models

CARLA

288 papers with code

AlphaStar

10 papers with code

See all 2 methods

RL Transformers

GTrXL

3 papers with code

CoBERL

1 papers with code

See all 2 methods

Exploration Strategies

Counterfactuals

296 papers with code

gSDE

1 papers with code

See all 2 methods

State Similarity Metrics

Policy Similarity Metric

1 papers with code

Playstyle Distance

1 papers with code

See all 2 methods

Motion Control

PPMC

1 papers with code

See all 2 methods

Policy Evaluation

KOVA

1 papers with code

See all 1 methods

Bayesian Reinforcement Learning

Bayesian REX

1 papers with code

See all 1 methods

Path Planning

PPMC

1 papers with code

See all 1 methods

Actor-Critic Algorithms

FORK

1 papers with code

See all 1 methods

Environment Design Methods

Protagonist Antagonist Induced Regret Environment Design

1 papers with code

See all 1 methods

Density Ratio Learning

GradientDICE

1 papers with code

See all 1 methods

Card Game Models

DouZero

3 papers with code

See all 1 methods