Papers with Code 아카이브
Montezuma's Revenge
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 3
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.
<span style="color:grey; opacity: 0.6">( Image credit: Q-map )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
PoE-World: Compositional World Modeling with Products of Programmatic Experts
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning
Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning
A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
Sample Efficient Deep Reinforcement Learning via Local Planning
Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments
Redeeming Intrinsic Rewards via Constrained Optimization
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
Paused Agent Replay Refresh
Cell-Free Latent Go-Explore
GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning
Parametrically Retargetable Decision-Makers Tend To Seek Power
Understanding and Preventing Capacity Loss in Reinforcement Learning
Open-Ended Reinforcement Learning with Neural Reward Functions
Generative Adversarial Exploration for Reinforcement Learning
Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning
On Bonus-Based Exploration Methods in the Arcade Learning Environment
Reinforcement Learning with Latent Flow
Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
First return, then explore
Exploring Unknown States with Action Balance
Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations
MIME: Mutual Information Minimisation Exploration
Uncertainty-sensitive Learning and Planning with Ensembles
DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning
Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards
Combining Experience Replay with Exploration by Random Network Distillation
Learning and Exploiting Multiple Subgoals for Fast Exploration in Hierarchical Reinforcement Learning
Using Natural Language for Reward Shaping in Reinforcement Learning
Go-Explore: a New Approach for Hard-Exploration Problems
Escape Room: A Configurable Testbed for Hierarchical Reinforcement Learning
Learning Montezuma's Revenge from a Single Demonstration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.