activity
20122026
most citedEmphatic Temporal-Difference Learning

21 citations · 131 across the 37 of their papers we have counts for

collaborators
Showing 2021 · cs.LGShow all

6 papers · 2 filters

cs.LG2021

Representation Alignment in Neural Networks

Ehsan Imani, Wei Hu, Martha White

It is now a standard for neural network representations to be trained on large, publicly available datasets, and used for new problems. The reasons for why neural network represent…

cs.LG2021★ 1 cited

Off-Policy Actor-Critic with Emphatic Weightings

Eric Graves, Ehsan Imani, Raksha Kumaraswamy +1

A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. T…

cs.LG2021★ 1 cited

Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning

Vincent Liu, James R. Wright, Martha White

Offline reinforcement learning -- learning a policy from a batch of data -- is known to be hard for general MDPs. These results motivate the need to look at specific classes of MDP…

cs.LG2021

Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences

Alan Chan, Hugo Silva, Sungsu Lim +3

Approximate Policy Iteration (API) algorithms alternate between (approximate) policy evaluation and (approximate) greedification. Many different approaches have been explored for a…

cs.LG2021

A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning

Andrew Patterson, Adam White, Martha White

Many reinforcement learning algorithms rely on value estimation, however, the most widely used algorithms -- namely temporal difference algorithms -- can diverge under both off-pol…

cs.LG2021

Scalable Online Recurrent Learning Using Columnar Neural Networks

Khurram Javed, Martha White, Rich Sutton

Structural credit assignment for recurrent learning is challenging. An algorithm called RTRL can compute gradients for recurrent networks online but is computationally intractable…