Methods › Reinforcement Learning
Reinforcement Learning
Collections are ordered by tagged papers; each shows its 5 most-tagged methods.
Off-Policy TD Control
5 methods · 1,854 papersQ-Learning
1,734 papers
Clipped Double Q-learning
122 papers
Double Q-learning
112 papers
Expected Sarsa
9 papers
Policy Gradient Methods
23 methods · 1,633 papersReplay Memory
2 methods · 933 papersExperience Replay
865 papers
Prioritized Experience Replay
138 papers
Value Function Estimation
6 methods · 610 papersQ-Learning Networks
9 methods · 532 papersOffline Reinforcement Learning Methods
5 methods · 485 papersHeuristic Search Algorithms
9 methods · 453 papersVideo Game Models
2 methods · 432 papersExploration Strategies
2 methods · 401 papersReinforcement Learning Frameworks
10 methods · 323 papersPOMO
6 papers
Board Game Models
3 methods · 155 papersOn-Policy TD Control
5 methods · 70 papersSarsa
56 papers
TD Lambda
14 papers
Expected Sarsa
9 papers
Sarsa Lambda
0 papers
True Online TD Lambda
0 papers
Randomized Value Functions
2 methods · 59 papersNoisy Linear Layer
11 papers
Distributed Reinforcement Learning
6 methods · 39 papersEligibility Traces
3 methods · 26 papersAccumulating Eligibility Trace
15 papers
Eligibility Trace
11 papers
Replacing Eligibility Trace
0 papers
Behaviour Policies
2 methods · 21 papersGo-Explore
16 papers
Epsilon Greedy Exploration
5 papers
Imitation Learning Methods
5 methods · 12 papersCLIPort
3 papers
Efficient Planning
1 method · 6 papersPrioritized Sweeping
6 papers
State Similarity Metrics
2 methods · 5 papersPlaystyle Distance
3 papers
Policy Similarity Metric
2 papers
Card Game Models
1 method · 4 papersDouZero
4 papers
RL Transformers
2 methods · 3 papersActor-Critic Algorithms
1 method · 1 paperBayesian Reinforcement Learning
1 method · 1 paperDensity Ratio Learning
1 method · 1 paperGradientDICE
1 paper