Papers with Code 아카이브
Efficient Exploration
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Efficient Exploration is one of the main obstacles in scaling up modern deep reinforcement learning algorithms. The main challenge in Efficient Exploration is the balance between exploiting current estimates, and gaining information about poorly understood states and actions.
Source: Randomized Value Functions via Multiplicative Normalizing Flows
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/pokaxpoka/sunrise
공식 코드SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
https://github.com/rail-berkeley/supe
공식 코드Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
https://github.com/raincchio/p3o
공식 코드https://github.com/rajammanabrolu/KG-DQN
공식 코드Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning
https://github.com/resibots/kaushik_2018_multi-dex
공식 코드Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards
https://github.com/revorg7/DeepSparseSampling
공식 코드https://github.com/ruqizhang/discrete-langevin
공식 코드https://github.com/ryeii/cdrm
공식 코드Disentangling Uncertainties by Learning Compressed Data Representation
https://github.com/s72sue/map-induction
공식 코드Map Induction: Compositional spatial submap learning for efficient exploration in novel environments
https://github.com/seungyulhan/dac
공식 코드Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
https://github.com/shengroup/mpmab_beacon
공식 코드Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization
https://github.com/smarttensors/geothermalcloud.jl
공식 코드GeoThermalCloud: Machine Learning for Geothermal Resource Exploration
https://github.com/srsohn/msgi
공식 코드Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
https://github.com/stavrosorf/dt4evs
공식 코드https://github.com/szrlee/GPT-HyperAgent
공식 코드https://github.com/szrlee/ensemble_plus_plus
공식 코드https://github.com/szrlee/hyperagent
공식 코드Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
https://github.com/tajwarfahim/paprika
공식 코드https://github.com/taochenshh/exp4nav
공식 코드https://github.com/taodav/nsrs
공식 코드Novelty Search in Representational Space for Sample Efficient Exploration
https://github.com/tianjunz/MADE
공식 코드MADE: Exploration via Maximizing Deviation from Explored Regions
https://github.com/tiantan522/PINs
공식 코드Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning
https://github.com/tlacombe/topt
공식 코드A Gradient Sampling Algorithm for Stratified Maps with Applications to Topological Data Analysis
https://github.com/tomdbar/ecord
공식 코드Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration
https://github.com/uber-research/Map-Elites-Evolutionary
공식 코드https://github.com/unitn-sml/pear-personalized-algorithmic-recourse
공식 코드Personalized Algorithmic Recourse with Preference Elicitation
https://github.com/unitn-sml/syn-interventions-algorithmic-recourse
공식 코드Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
https://github.com/uoe-agents/lb-foraging
공식 코드Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
https://github.com/uoe-agents/seac
공식 코드Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
https://github.com/uzh-rpg/foresight-nav
공식 코드ForesightNav: Learning Scene Imagination for Efficient Exploration
https://github.com/vdean/audio-curiosity
공식 코드https://github.com/vidalt/HGS-CVRP
공식 코드Hybrid Genetic Search for the CVRP: Open-Source Implementation and SWAP* Neighborhood
https://github.com/wiseodd/lapeft-bayesopt
공식 코드https://github.com/wyhwhy/Amortized-Variational-DQN
공식 코드https://github.com/xf-zhao/iscm
공식 코드Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.