Papers with Code 아카이브
OpenAI Gym
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 17
- 보존된 평가 기록
- 45
An open-source toolkit from OpenAI that implements several Reinforcement Learning benchmarks including: classic control, Atari, Robotics and MuJoCo tasks.
(Description by Evolutionary learning of interpretable decision trees)
(Image Credit: OpenAI Gym)
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
The PlayStation Reinforcement Learning Environment (PSXLE)
Playing Games in the Dark: An approach for cross-modality transfer in reinforcement learning
Accelerating Reinforcement Learning with Suboptimal Guidance
Gym-Ignition: Reproducible Robotic Simulations for Reinforcement Learning
Challenging On Car Racing Problem from OpenAI gym
Towards a Reinforcement Learning Environment Toolbox for Intelligent Electric Motor Control
Zap Q-Learning With Nonlinear Function Approximation
MVFST-RL: An Asynchronous RL Framework for Congestion Control with Delayed Actions
TorchBeast: A PyTorch Platform for Distributed RL
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
SURREAL-System: Fully-Integrated Stack for Distributed Deep Reinforcement Learning
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning
Active inference: demystified and compared
MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning
Recommendation System-based Upper Confidence Bound for Online Advertising
Learning sparse representations in reinforcement learning
Arena: a toolkit for Multi-Agent Reinforcement Learning
A Dual Memory Structure for Efficient Use of Replay Memory in Deep Reinforcement Learning
QFlip: An Adaptive Reinforcement Learning Strategy for the FlipIt Security Game
Proximal Distilled Evolutionary Reinforcement Learning
Reward Prediction Error as an Exploration Objective in Deep RL
MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning
Towards Interactive Training of Non-Player Characters in Video Games
Decision-Making in Reinforcement Learning
Provably Efficient Imitation Learning from Observation Alone
Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment
Maximum Entropy-Regularized Multi-Goal Reinforcement Learning
Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction
Design of Artificial Intelligence Agents for Games using Deep Reinforcement Learning
Deep Ordinal Reinforcement Learning
Towards Combining On-Off-Policy Methods for Real-World Applications
Evolving Neural Networks in Reinforcement Learning by means of UMDAc
Towards Brain-inspired System: Deep Recurrent Reinforcement Learning for Simulated Self-driving Agent
DQN with model-based exploration: efficient learning on environments with sparse rewards
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.