Picture for Tanmay Gangwani

Tanmay Gangwani

Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow

Add code
Nov 22, 2023
Viaarxiv icon

Selective Uncertainty Propagation in Offline RL

Add code
Feb 01, 2023
Viaarxiv icon

Imitation Learning from Observations under Transition Model Disparity

Add code
Apr 25, 2022
Figure 1 for Imitation Learning from Observations under Transition Model Disparity
Figure 2 for Imitation Learning from Observations under Transition Model Disparity
Figure 3 for Imitation Learning from Observations under Transition Model Disparity
Figure 4 for Imitation Learning from Observations under Transition Model Disparity
Viaarxiv icon

Hindsight Foresight Relabeling for Meta-Reinforcement Learning

Add code
Sep 18, 2021
Figure 1 for Hindsight Foresight Relabeling for Meta-Reinforcement Learning
Figure 2 for Hindsight Foresight Relabeling for Meta-Reinforcement Learning
Figure 3 for Hindsight Foresight Relabeling for Meta-Reinforcement Learning
Figure 4 for Hindsight Foresight Relabeling for Meta-Reinforcement Learning
Viaarxiv icon

Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity

Add code
Nov 05, 2020
Figure 1 for Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity
Figure 2 for Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity
Figure 3 for Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity
Figure 4 for Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity
Viaarxiv icon

Learning Guidance Rewards with Trajectory-space Smoothing

Add code
Oct 23, 2020
Figure 1 for Learning Guidance Rewards with Trajectory-space Smoothing
Figure 2 for Learning Guidance Rewards with Trajectory-space Smoothing
Figure 3 for Learning Guidance Rewards with Trajectory-space Smoothing
Figure 4 for Learning Guidance Rewards with Trajectory-space Smoothing
Viaarxiv icon

Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch

Add code
Jun 12, 2020
Figure 1 for Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch
Figure 2 for Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch
Figure 3 for Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch
Figure 4 for Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch
Viaarxiv icon

State-only Imitation with Transition Dynamics Mismatch

Add code
Feb 27, 2020
Figure 1 for State-only Imitation with Transition Dynamics Mismatch
Figure 2 for State-only Imitation with Transition Dynamics Mismatch
Figure 3 for State-only Imitation with Transition Dynamics Mismatch
Figure 4 for State-only Imitation with Transition Dynamics Mismatch
Viaarxiv icon

Learning Belief Representations for Imitation Learning in POMDPs

Add code
Jun 22, 2019
Figure 1 for Learning Belief Representations for Imitation Learning in POMDPs
Figure 2 for Learning Belief Representations for Imitation Learning in POMDPs
Figure 3 for Learning Belief Representations for Imitation Learning in POMDPs
Figure 4 for Learning Belief Representations for Imitation Learning in POMDPs
Viaarxiv icon

Learning Self-Imitating Diverse Policies

Add code
May 25, 2018
Figure 1 for Learning Self-Imitating Diverse Policies
Figure 2 for Learning Self-Imitating Diverse Policies
Figure 3 for Learning Self-Imitating Diverse Policies
Figure 4 for Learning Self-Imitating Diverse Policies
Viaarxiv icon