Group Meetings
If you would like to get notifications about the group meetings and other matters, please email Marek.Petrik@unh.edu to be added to the mailing list.
Fall 2022
When: Thursdays 1pm - 2pm
Where: Zoom: https://unh.zoom.us/j/5833938643
| Date | Topic | Presenter |
|---|---|---|
| Sep 15 | Organizational meeting | Marek |
Summer 2022
When: Thursday 12:00pm - 1:00pm
Where: Kingsbury N233
Reading convex optimization by Boyd.
Spring 2022
When: Thursday 10:00am - 11:00am
Where: Kingsbury N233
| Date | Topic | Presenter |
|---|---|---|
| Feb 10 | General discussion | General meeting |
| Feb 17 | Practice talk | Monkie |
| Feb 24 | On the convergence of policy iteration | Harrison |
| Mar 03 | Poisoning policy evaluation | Elita |
| Mar 10 | RASR | Monkie |
| Mar 17 | Spring break | |
| Mar 24 | Variational Bayesian RL | Bahram |
| Mar 31 | Entropic MDPs | Marek |
| Apr 07 | Near Optimal Bayesian Ambiguity | Marek and Elita |
| Apr 14 | Yash Chandak | |
| Apr 21 | Bahram | |
| Apr 28 | Saba | |
| May 05 | Xihong |
Fall 2021
When: Wednesday 2:00 - 3:00
Where: Kingsbury N233, and Zoom
| Date | Topic | Presenter |
|---|---|---|
| Sep 15 | Proposal practice talk | Bahram |
| Sep 22 | SQIL | Soheil |
| Sep 29 | Stochastic programs with entropic risk | Monkie |
| Oct 06 | Generalized IRL for linear MDPs | Saba |
| Oct 13 | Canceled | |
| Oct 20 | Linearly solvable MDPs | Marek |
| Oct 27 | Optimal Off-Policy Evaluation from Multiple Logging Policies | Elita |
| Nov 03 | Gravitational Pull of Softmax | Gerry |
| Nov 10 | Optimality of Policy Gradient | Soheil |
| Nov 17 | Multimodel MDP | Xihong |
| Nov 24 | Thanksgiving | |
| Dec 01 | Accelerated VI | Harrison |
| Dec 08 | Neurips |
Spring 2021
When: Thursday 9:30 - 10:30
Where: Zoom
| Date | Topic | Presenter |
|---|---|---|
| 1/28 | Algorithmic imitation learning | Soheil |
| 2/04 | Open problem: Convex formulation RMDP | Marek |
| 2/11 | BROIL | Gerry |
| 2/18 | Policy poisoning in batch RL | Elita |
| 2/25 | Distributionally Robust MDPs | Monkie |
| 3/04 | Offline RL | Bahram |
| 3/11 | Epistemic Risk-Sensitive RL | Reazul |
| 3/18 | Break | |
| 3/25 | Break | |
| 4/01 | Reward machines | Colin |
| 4/08 | Break | |
| 4/15 | Resource-constrained DRL | Elita |
| 4/22 | Statistical limits of offline RL | Saba |
| 4/29 | Break | |
| 5/06 | IRL via Classificiation | Gerry |
Other papers:
Progress update meetings:
When: Tuesday 9:30 - 11:30
- Short update: Anyone present: 5 minutes
- Long update: up to 20 minutes including discussion:
Long updates: even weeks: Elita, Monkie, Reazul, odd weeks: Bahram, Soheil, Devin
Fall 2020
When: Tuesday 12pm
Where: Zoom
| Date | Topic | Presenter |
|---|---|---|
| 09/22 | Accelerated Value Iteration | Marek |
| 09/29 | Bias and Variance Approximation in Value Function Estimates | Monkie |
| 10/06 | Soheil | |
| 10/13 | Colin | |
| 10/20 | State aggregation learning | Sepideh |
| 10/27 | Proposal? | Devin |
| 11/03 | Proposal practice | Reazul |
| 11/10 | Application! | Marek |
| 11/17 | Proposal practice | Chris |
| 11/24 | Proposal practice | Bahram |
Summer 2020
When: Wednesday 9am - 10am
Where: Zoom (mailing list for link)
| Date | Topic | Presenter |
|---|---|---|
| 5/27 | Inverse RL and Robustness | Soheil |
| 6/03 | Optimizer’s Curse | Lynette |
| 6/10 | Risk and Robustness CVaR | Monkie |
| 6/17 | Deep RL and Energy | Saba |
| 6/24 | Polyanimals project | Chris |
| 7/01 | Interpretable off-policy eval | Elita |
| 7/08 | Lasso | Devin |
| 7/15 | Safe Policy Improvement | Bahram |
| 7/22 | Inverse RL | Mostafa |
| 7/29 | Review | Marek |
Spring 2020
When: Wednesday 3:30pm - 4:30pm
Where: Kingsbury N242
Ski-trip: Sat Feb 15th, 2020
| Date | Topic | Presenter |
|---|---|---|
| Jan 29 | Intrinsically Efficient … Off-Policy Evaluation | Bahram |
| Feb 05 | Percentile Optimization for MDPs | Monkie |
| Feb 12 | Proposal: Robust POMDPs | Devin |
| Feb 19 | Robust IRL | Soheil |
| Feb 26 | Proposal: Spruce Budworm | Jason |
| Mar 04 | Policy Gradient for Coherent Risk Measures | Talha |
| Mar 11 | Poly-animals | Chris |
| Mar 18 | Spring break |
Coronavirus …..
Fall 2019
When: Thursday 11:00am - 12:30pm, some days 10:30 - 12:00
Where: Kingsbury N233
| Date | Topic | Presenter |
|---|---|---|
| Sep 19 | Fingerprint policy optimization | Bahram |
| Sep 26 | Action Robust Reinforcement Learning | Shayan |
| Oct 03 | Robust Risk-Averse Sequential Decision Making | Jason |
| Oct 10 | Optimizing Norm-bounded Weighted Ambiguity Sets for Robust MDPs | Reazul |
| Oct 17 | POMDPs easy to approximate | Monkie |
| Oct 24 | MaxEnt IRL | Soheil |
| Oct 31 | Point-based value iteration: An anytime algorithm for POMDPs | Xihong |
| Nov 07 | Likelihood analysis of species occurrence probability from presence-only data for modelling species distributions | Chris |
| Nov 14 | Concentration Inequalities for CVaR | Talha |
| Nov 21 | Rasel | |
| Nov 28 | Thanksgiving | |
| Dec 05 | Marek |
Summer 2019
When: Wednesday 12:30pm - 1:30pm
Where: Kingsbury N233
Also: Pizza
| Date | Topic | Presenter |
|---|---|---|
| May 29 | Near-OptimalBayesianAmbiguity Sets | Marek |
| Jun 05 | Uncertainty Analysis of Species Distribution Models | Saba |
| Jun 12 | Robust and risk averse MDPs | Jason |
| Jun 19 | Deep Reinforcement Learning … | Xihong |
| Jun 26 | Bahram | |
| Jul 03 | Monkey & Talha | |
| Jul 17 | Reazul | |
| Jul 24 | Chris or Soheil | |
| Jul 31 | Jordan |
Spring 2019
When: Monday 3:30pm - 4:30pm
Where: Kingsbury N242
| Date | Topic | Presenter |
|---|---|---|
| Jan 28 | Introduction | Marek |
| Feb 04 | Optimism in the Face of Value Functions | Reazul and Tianyi |
| Feb 11 | Adversarial Attacks on Neural Policies | Shayan |
| Feb 18 | Performance Loss Bounds for Approximate Value Iteration with State Aggregation | Soheil |
| Feb 25 | Near-OptimalBayesianAmbiguity Sets | Bahram |
| Mar 04 | R-rectangular | Saba |
| Mar 11 | Spring Break | |
| Mar 18 | Greenhouse and other stuff | Sangeeta or Chris |
| Mar 25 | Robustness to confounding factors | Monkie |
| Apr 01 | Bear world | Chris |
| Apr 08 | MMS | Samantha |
| Apr 15 | Canceled | |
| Apr 22 | Original results | Reazul |
| Apr 29 | Distributional heuristic functions | Tianyi |
| May 06 | SBEED | Marek |
Fall 2018
When: Monday 2:00pm - 3:00pm
Where: Kingsbury N233
| Date | Day | Topic | Presenter |
|---|---|---|---|
| Sep 10 | Mon | Summer Review | |
| Sep 17 | Mon | Planning in the Presence of Cost Functions Controlled by an Adversary | Jason |
| Sep 24 | Mon | Bayesian Distributional Robustness | Marek |
| Oct 01 | Mon | A data-driven, machine learning framework for optimal pest management in cotton | Chris |
| Oct 09 | Tue | Policy Conditioned Uncertainty Sets for Robust MDPs | Bahram |
| Oct 15 | Mon | Canceled | |
| Oct 22 | Mon | (More) Efficient Reinforcement Learning via Posterior Sampling | Tianyi |
| Oct 29 | Mon | Reinforcement learning with basis construction … | Soheil |
| Nov 05 | Mon | Finding Magnetopause | Samantha |
| Nov 12 | Mon | Veteran’s day | |
| Nov 19 | Mon | Bayesian robust RL | Reazul |
| Nov 26 | Mon | Optimization for Greenhouses | Chris |
| Dec 03 | Mon | Canceled | |
| Dec 10 | Mon | NIPS report | Marek and Reazul |
Summer 2018
When: Wednesday 12:00pm - 1:00pm
Where: Kingsbury N233
Also: Pizza
| Date | Speaker | Topic |
|---|---|---|
| May 16 | Marek (Andreas) | Computing Robust Strategies for Managing Invasive Plants |
| May 23 | Marek | Fast Robust Bellman Updates |
| May 30 | Coral (Rachel) | Autonomous Vehicle Navigation in Rural Environments without Detailed Prior Maps |
| June 6 | Bahram (Jordan) | Low-Rank Value Function Approximation for Co-optimization of Battery Storage |
| June 13 | Jason (Shayan) | Minimax Regret Bounds for Reinforcement Learning |
| June 20 | Monkie | MDPs for Playing Blackjack |
| June 27 | Shayan | MaxLike for Species Distribution Models |
| July 4 | No meeting |
Spring 2018
When: Wednesday 4:00pm - 5:00pm
Where: Kingsbury N233
Also: Refreshments
| Date | Speaker | Topic |
|---|---|---|
| Feb 21 | Bahram | Sparsity and LASSO |
| Feb 28 | Reazul | Robust Adversarial Reinforcement Learning |
| Mar 21 | Jordan | Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes |
| Mar 28 | Coral | Adaptive Neural Network Control of AUVs With Control Input Nonlinearities Using Reinforcement Learning |
| Apr 4 | Shayan | Safe Policy Improvement by Minimizing Robust Baseline Regret |
| Apr 11 | Marek | Risk-aversion tutorial |
| Apr 18 | Rachel | PAC Optimal MDP Planning with Application to Invasive Species Management |
| Apr 25 | Jason | Safe Policy Improvement with Baseline Bootstrapping |
| May 2 | Bahram | Markov decision processes |
| May 9 | Marek | How to be a graduate student |
Winter 2018
Joint meetings with Wheeler’s group.
When: Wednesday 12:00pm - 1:00pm
Where: Kingsbury N233
Also: Pizza
| Date | Paper |
|---|---|
| Jan 3 | DESPOT |
| Jan 10 | Robust MDPs |
| Jan 17 | TDTS |
Fall 2017
When: Friday 10:00am - 11:00am
Where: Kingsbury N233
| Date | Speaker | Topic |
|---|---|---|
| Sep 01 | Marek | Fast s-rectangular robustness |
| Sep 08 | Bahram | Linear feature encoding |
| Sep 15 | Bence | Meeting canceled, Bence at robotics seminar: 12:10-1pm in Kingsbury N101 |
| Sep 22 | Jordan | Meta-modeling and spatial analysis |
| Sep 29 | (Hala) | |
| Oct 06 | Reazul | Bayesian robust ambiguity sets |
| Oct 13 | Andreas | Maximum entropy for species distributions |
| Oct 20 | Marek | Minimizing Regret in MDPs |
| Oct 27 | Bence + Jordan | Active learning and MaxEnt |
| Nov 03 | Talha | Practical Precautionary Resource Management Using Robust Optimization |
| Nov 10 | Veteran’s day | |
| Nov 17 | Nobody | |
| Nov 24 | Thanksgiving | |
| Dec 01 | Jordan | |
| Dec 08 | Bence | LinUCB |