Search Results for author:
Found 13 papers, 4 papers with code
A Theory for Length Generalization in Learning to Reason
Length generalization (LG) is a challenging problem in learning to reason.
Conditions for Length Generalization in Learning Reasoning Skills
However, numerous evaluations of the reasoning capabilities of LLMs have also showed some limitations.
Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
The key theoretical result is that regardless of whether WP and OOD detection (or TP) are defined explicitly or implicitly by a CIL algorithm, good WP and good OOD detection are necessary and sufficient conditions for good CIL, which unifies novelty or OOD detection and continual learning (CIL, in particular).
Mastering Strategy Card Game (Hearthstone) with Improved Techniques
Strategy card game is a well-known genre that is demanding on the intelligent game-play and can be an ideal test-bench for AI.
Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play
Deep Reinforcement Learning combined with Fictitious Play shows impressive results on many benchmark games, most of which are, however, single-stage.
A Theoretical Study on Solving Continual Learning
Continual learning (CL) learns a sequence of tasks incrementally.
Generalized Data Distribution Iteration
Then, we cast these two problems into the training data distribution optimization problem, namely to obtain desired training data within limited interactions, and address them concurrently via i) explicit modeling and control of the capacity and diversity of behavior policy and ii) more fine-grained and adaptive control of selective/sampling distribution of the behavior policy using a monotonic data distribution optimization.
Ranked #1 on
Atari Games
on atari game
Continual Learning Based on OOD Detection and Task Masking
Existing continual learning techniques focus on either task incremental learning (TIL) or class incremental learning (CIL) problem, but not both.
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
Deep Q Network (DQN) firstly kicked the door of deep reinforcement learning (DRL) via combining deep learning (DL) with reinforcement learning (RL), which has noticed that the distribution of the acquired data would change during the training process.
Ranked #1 on
Atari Games
on Atari 2600 Freeway
An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning
We find valued-based reinforcement learning methods with {\epsilon}-greedy mechanism are capable of enjoying three characteristics, Closed-form Diversity, Objective-invariant Exploration and Adaptive Trade-off, which help value-based methods avoid the policy collapse problem.
CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration
We study the problem of model-free reinforcement learning, which is often solved following the principle of Generalized Policy Iteration (GPI).
Hierarchical Meta Reinforcement Learning for Multi-Task Environments
To address the problem brought by the environment, we propose a Meta Soft Hierarchical reinforcement learning framework (MeSH), in which each low-level sub-policy focuses on a specific sub-task respectively and high-level policy automatically learns to utilize low-level sub-policies through meta-gradients.
Hierarchical Reinforcement Learning
Meta Reinforcement Learning
+2
