https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-
공식 코드Combining Experience Replay with Exploration by Random Network Distillation
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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/NeteaseFuxiRL/action-balance-exploration
공식 코드https://github.com/WendyShang/dqn_zoo
공식 코드https://github.com/WendyShang/flare
공식 코드https://github.com/amujika/open-ended-reinforcement-learning-with-neural-reward-functions
공식 코드Open-Ended Reinforcement Learning with Neural Reward Functions
https://github.com/awjuliani/deep-rl-plasticity
공식 코드A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
https://github.com/bartekcupial/finetuning-rl-as-cl
공식 코드Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
https://github.com/facebookresearch/e3b
공식 코드A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
https://github.com/gomiss/action-balance-exploration
공식 코드https://github.com/google-research/google-research
공식 코드Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
https://github.com/grockious/deepsynth
공식 코드DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning
https://github.com/improbable-ai/eipo
공식 코드https://github.com/navneet-nmk/pytorch-rl
공식 코드Empowerment-driven Exploration using Mutual Information Estimation
https://github.com/openai/random-network-distillation
공식 코드https://github.com/qgallouedec/lge
공식 코드https://github.com/samlobel/cfn
공식 코드Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning
https://github.com/topwasu/poe-world
공식 코드PoE-World: Compositional World Modeling with Products of Programmatic Experts
https://github.com/uber-research/go-explore
공식 코드https://github.com/yudasong/hyq
공식 코드Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
https://github.com/Adeikalam/Go-Explore
https://github.com/BY571/DQN-Atari-Agents
Rainbow: Combining Improvements in Deep Reinforcement Learning
https://github.com/Curt-Park/rainbow-is-all-you-need
Rainbow: Combining Improvements in Deep Reinforcement Learning
https://github.com/Dorozhko-Anton/go-explore
https://github.com/DuaneNielsen/rnd
https://github.com/JayLohokare/banana-world-navigation
Rainbow: Combining Improvements in Deep Reinforcement Learning
https://github.com/Justkim/random-network-distillation-pytorch
https://github.com/Kaixhin/Rainbow
Rainbow: Combining Improvements in Deep Reinforcement Learning
https://github.com/LeejwUniverse/RL_Exploration_Pytorch
https://github.com/MaxSobolMark/HardRLWithYoutube
https://github.com/Narsil/rl-baselines
https://github.com/RLAgent/state-marginal-matching
https://github.com/alirezakazemipour/ppo-rnd
https://github.com/amzoyang/CS-221-Final-Project
Rainbow: Combining Improvements in Deep Reinforcement Learning
https://github.com/atavakol/action-hypergraph-networks
Rainbow: Combining Improvements in Deep Reinforcement Learning
https://github.com/bacdavid/RND-O
https://github.com/balloch/rl-exploration-transfer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.