Reinforcement Learning
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
Human beings are able to transfer the policies swiftly to a structurally similar task.
Learning World Models for Unconstrained Goal Navigation
Learning world models offers a promising avenue for goal-conditioned reinforcement learning with sparse rewards. By allowing agents to plan actions or exploratory goals without direct interaction with the environment, world models enhance exploration efficiency. The quality of a world model hinges on the richness of data stored in the agent's replay buffer, with expectations of reasonable
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation Long-Fei Li
Reinforcement Learning (RL) with function approximation has achieved remarkable success in various applications involving large state and action spaces, such as games [Silver et al., 2016],
Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
Additionally, methods that utilize the bisimulation metric for evaluating state discrepancies face a theory-practice gap due to improper approximations in metric learning, particularly struggling with hard exploration tasks.
GT A: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
Offline Reinforcement Learning (Offline RL) presents challenges of learning effective decision-making policies from static datasets without any online interactions.
