Search Results for author:
Found 9 papers, 1 papers with code
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
We fine tune this model to obtain a Searchformer, a Transformer model that optimally solves previously unseen Sokoban puzzles 93. 7% of the time, while using up to 26. 8% fewer search steps than the $A^*$ implementation that was used for training initially.
IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control
Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset.
Reward-Predictive Clustering
Recent advances in reinforcement-learning research have demonstrated impressive results in building algorithms that can out-perform humans in complex tasks.
Successor Features Combine Elements of Model-Free and Model-based Reinforcement Learning
A key question in reinforcement learning is how an intelligent agent can generalize knowledge across different inputs.
Mitigating Planner Overfitting in Model-Based Reinforcement Learning
An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model.
Transfer with Model Features in Reinforcement Learning
Further, we present a Successor Feature model which shows that learning Successor Features is equivalent to learning a Model-Reduction.
State Abstractions for Lifelong Reinforcement Learning
We introduce two new classes of abstractions: (1) transitive state abstractions, whose optimal form can be computed efficiently, and (2) PAC state abstractions, which are guaranteed to hold with respect to a distribution of tasks.
Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning
One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks.
Policy Gradient Methods for Off-policy Control
Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy.
