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 1–50 of 61 papers

TitleStatusHype
Action-Dependent Optimality-Preserving Reward Shaping—0
PoE-World: Compositional World Modeling with Products of Programmatic ExpertsCode1
A Study of Plasticity Loss in On-Policy Deep Reinforcement LearningCode0
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation ProblemCode0
Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning—0
Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement LearningCode1
A Study of Global and Episodic Bonuses for Exploration in Contextual MDPsCode1
Sample Efficient Deep Reinforcement Learning via Local Planning—0
Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments—0
Redeeming Intrinsic Rewards via Constrained OptimizationCode1
Hybrid RL: Using Both Offline and Online Data Can Make RL EfficientCode1
Paused Agent Replay Refresh—0
Cell-Free Latent Go-ExploreCode1
GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning—0
Parametrically Retargetable Decision-Makers Tend To Seek Power—0
Understanding and Preventing Capacity Loss in Reinforcement Learning—0
Open-Ended Reinforcement Learning with Neural Reward FunctionsCode1
Generative Adversarial Exploration for Reinforcement Learning—0
Exploration by Random Network Distillation—0
Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning—0
Entropic Desired Dynamics for Intrinsic Control—0
NovelD: A Simple yet Effective Exploration CriterionCode1
On Bonus-Based Exploration Methods in the Arcade Learning Environment—0
Reinforcement Learning with Latent FlowCode1
Learning Abstract Models for Strategic Exploration and Fast Reward TransferCode0
First return, then exploreCode1
Exploring Unknown States with Action BalanceCode0
Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations—0
MIME: Mutual Information Minimisation Exploration—0
On Bonus Based Exploration Methods In The Arcade Learning Environment—0
Uncertainty-sensitive Learning and Planning with EnsemblesCode0
DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement LearningCode0
Uncertainty - sensitive learning and planning with ensemblesCode0
Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment—0
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards—0
Combining Experience Replay with Exploration by Random Network DistillationCode0
Learning and Exploiting Multiple Subgoals for Fast Exploration in Hierarchical Reinforcement Learning—0
Using Natural Language for Reward Shaping in Reinforcement LearningCode0
Go-Explore: a New Approach for Hard-Exploration ProblemsCode1
Escape Room: A Configurable Testbed for Hierarchical Reinforcement Learning—0
Learning Montezuma's Revenge from a Single Demonstration—0
Contingency-Aware Exploration in Reinforcement Learning—0
Exploration by Random Network DistillationCode1
Learning Representations in Model-Free Hierarchical Reinforcement Learning—0
Empowerment-driven Exploration using Mutual Information EstimationCode0
Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural NetworksCode0
Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems—0
Observe and Look Further: Achieving Consistent Performance on Atari—0
Playing hard exploration games by watching YouTubeCode1
Hierarchical Imitation and Reinforcement Learning—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.