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

Showing 2130 of 61 papers

TitleStatusHype
Count-Based Exploration with Neural Density ModelsCode0
Learning Abstract Models for Strategic Exploration and Fast Reward TransferCode0
Beating Atari with Natural Language Guided Reinforcement LearningCode0
A Study of Plasticity Loss in On-Policy Deep Reinforcement LearningCode0
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation ProblemCode0
Empowerment-driven Exploration using Mutual Information EstimationCode0
DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement LearningCode0
Combining Experience Replay with Exploration by Random Network DistillationCode0
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic MotivationCode0
Unifying Count-Based Exploration and Intrinsic MotivationCode0
Show:102550
← PrevPage 3 of 7Next →

No leaderboard results yet.