Picture for Dharmashankar Subramanian

Dharmashankar Subramanian

Policy Gradients for Probabilistic Constrained Reinforcement Learning

Oct 02, 2022
Weiqin Chen, Dharmashankar Subramanian, Santiago Paternain

Figure 1 for Policy Gradients for Probabilistic Constrained Reinforcement Learning

Figure 2 for Policy Gradients for Probabilistic Constrained Reinforcement Learning

Figure 3 for Policy Gradients for Probabilistic Constrained Reinforcement Learning

Access Paper or Ask Questions

Learning Temporal Rules from Noisy Timeseries Data

Feb 11, 2022
Karan Samel, Zelin Zhao, Binghong Chen, Shuang Li, Dharmashankar Subramanian, Irfan Essa, Le Song

* 19 pages, 5 figures

Access Paper or Ask Questions

Edge-augmented Graph Transformers: Global Self-attention is Enough for Graphs

Aug 07, 2021
Md Shamim Hussain, Mohammed J. Zaki, Dharmashankar Subramanian

Figure 1 for Edge-augmented Graph Transformers: Global Self-attention is Enough for Graphs

Figure 2 for Edge-augmented Graph Transformers: Global Self-attention is Enough for Graphs

Figure 3 for Edge-augmented Graph Transformers: Global Self-attention is Enough for Graphs

Figure 4 for Edge-augmented Graph Transformers: Global Self-attention is Enough for Graphs

* 17 pages, 1 figure, 4 tables

Access Paper or Ask Questions

Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation

Sep 26, 2013
Marek Petrik, Dharmashankar Subramanian, Janusz Marecki

Figure 1 for Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation

Figure 2 for Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation

Figure 3 for Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation

Figure 4 for Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation

* Appears in Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013)

Access Paper or Ask Questions

An Approximate Solution Method for Large Risk-Averse Markov Decision Processes

Oct 16, 2012
Marek Petrik, Dharmashankar Subramanian

Figure 1 for An Approximate Solution Method for Large Risk-Averse Markov Decision Processes

Figure 2 for An Approximate Solution Method for Large Risk-Averse Markov Decision Processes

Figure 3 for An Approximate Solution Method for Large Risk-Averse Markov Decision Processes

Figure 4 for An Approximate Solution Method for Large Risk-Averse Markov Decision Processes

* Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012)

Access Paper or Ask Questions