1 citations · 1 across the 4 of their papers we have counts for
7 papers · 1 filter
Semantic World Models
Jacob Berg, Chuning Zhu, Yanda Bao +2
Planning with world models offers a powerful paradigm for robotic control. Conventional approaches train a model to predict future frames conditioned on current frames and actions,…
ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning
Eddy Hudson, Ishan Durugkar, Garrett Warnell +1
Given a dataset of expert agent interactions with an environment of interest, a viable method to extract an effective agent policy is to estimate the maximum likelihood policy indi…
Wasserstein Distance Maximizing Intrinsic Control
Ishan Durugkar, Steven Hansen, Stephen Spencer +1
This paper deals with the problem of learning a skill-conditioned policy that acts meaningfully in the absence of a reward signal. Mutual information based objectives have shown so…
Adversarial Intrinsic Motivation for Reinforcement Learning
Ishan Durugkar, Mauricio Tec, Scott Niekum +1
Learning with an objective to minimize the mismatch with a reference distribution has been shown to be useful for generative modeling and imitation learning. In this paper, we inve…
Reducing Sampling Error in Batch Temporal Difference Learning
Brahma Pavse, Ishan Durugkar, Josiah Hanna +1
Temporal difference (TD) learning is one of the main foundations of modern reinforcement learning. This paper studies the use of TD(0), a canonical TD algorithm, to estimate the va…
Multi-Preference Actor Critic
Ishan Durugkar, Matthew Hausknecht, Adith Swaminathan +1
Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for m…