SOTAVerified

Reinforcement Learning (RL)

Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1091–1100 of 15113 papers

TitleStatusHype
On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic ForgettingCode1
ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual ActorCode1
IGLU Gridworld: Simple and Fast Environment for Embodied Dialog AgentsCode1
RLx2: Training a Sparse Deep Reinforcement Learning Model from ScratchCode1
On the Robustness of Safe Reinforcement Learning under Observational PerturbationsCode1
Provable Benefits of Representational Transfer in Reinforcement LearningCode1
Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective TrajectoriesCode1
Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming ChallengesCode1
Learning to Solve Combinatorial Graph Partitioning Problems via Efficient ExplorationCode1
FedFormer: Contextual Federation with Attention in Reinforcement LearningCode1
Show:102550
← PrevPage 110 of 1512Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PPGMean Normalized Performance0.76—Unverified
2PPOMean Normalized Performance0.58—Unverified