SOTAVerified

Montezuma's Revenge

Montezuma's Revenge is an ATARI 2600 Benchmark game that is known to be difficult to perform on for reinforcement learning algorithms. Solutions typically employ algorithms that incentivise environment exploration in different ways.

For the state-of-the art tables, please consult the parent Atari Games task.

( Image credit: Q-map )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 61 papers

TitleStatusHype
Rainbow: Combining Improvements in Deep Reinforcement LearningCode3
Cell-Free Latent Go-ExploreCode1
Go-Explore: a New Approach for Hard-Exploration ProblemsCode1
A Study of Global and Episodic Bonuses for Exploration in Contextual MDPsCode1
Redeeming Intrinsic Rewards via Constrained OptimizationCode1
First return, then exploreCode1
Open-Ended Reinforcement Learning with Neural Reward FunctionsCode1
NovelD: A Simple yet Effective Exploration CriterionCode1
Playing hard exploration games by watching YouTubeCode1
Hybrid RL: Using Both Offline and Online Data Can Make RL EfficientCode1
Reinforcement Learning with Latent FlowCode1
Exploration by Random Network DistillationCode1
Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement LearningCode1
PoE-World: Compositional World Modeling with Products of Programmatic ExpertsCode1
Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems—0
Deep Abstract Q-Networks—0
Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations—0
Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments—0
Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning—0
Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment—0
Hierarchical Imitation and Reinforcement Learning—0
Exploration in Feature Space for Reinforcement Learning—0
Exploration by Random Network Distillation—0
Action-Dependent Optimality-Preserving Reward Shaping—0
Escape Room: A Configurable Testbed for Hierarchical Reinforcement Learning—0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.