Reinforcement Learning
Average-Reward Learning and Planning with Options Yi Wan, Abhishek Naik, Richard S. Sutton {wan6,anaik1,rsutton }@ualberta.ca University of Alberta, Amii
We extend the options framework for temporal abstraction in reinforcement learning from discounted Markov decision processes (MDPs) to average-reward MDPs. Our contributions include general convergent off-policy inter-option learning algorithms, intra-option algorithms for learning values and models, as well as sample-based planning variants of our learning algorithms. Our algorithms and convergence proofs extend those recently developed by Wan, Naik, and Sutton.
MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning Y ao Lai Y ao Mu Ping Luo Department of Computer Science The University of Hong Kong {ylai,ymu,pluo }@cs.hku.hk
Firstly, MaskPlace recasts placement as a problem of learning pixel-level visual representation to comprehensively describe millions of modules on a chip, enabling placement in a high-resolution canvas and a large action space. It outperforms recent methods that represent a chip as a hypergraph.
Information-theoretic Task Selection for Meta-Reinforcement Learning
A common framework consists in modeling the range of tasks the agent may encounter as a distribution over all possible tasks.
Supplementary: Reinforcement Learning Enhanced Explainer for Graph Neural Networks Caihua Shan
(line 4). We show our RG-Explainer for graph classification in Alg. 2. The algorithm is similar to the one explaining node classifications, except that we train our seed locator to detect the most influential (line 4). Input: The input graph G = ( V, E), node features X, node instances I, and a trained GNN model f () . Check the stopping criteria by Eq. 10. I, and a trained GNN model f () .
First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs Ben Norman
The objective is to maximize the total reward accumulated over all episodes (e.g., the number of games won), expressed as