Picture for Takato Okudo

Takato Okudo

Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning

Add code
Apr 13, 2021
Figure 1 for Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
Figure 2 for Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
Figure 3 for Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
Figure 4 for Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
Viaarxiv icon

Reward Shaping with Subgoals for Social Navigation

Add code
Apr 13, 2021
Figure 1 for Reward Shaping with Subgoals for Social Navigation
Figure 2 for Reward Shaping with Subgoals for Social Navigation
Figure 3 for Reward Shaping with Subgoals for Social Navigation
Figure 4 for Reward Shaping with Subgoals for Social Navigation
Viaarxiv icon

Reward Shaping with Dynamic Trajectory Aggregation

Add code
Apr 13, 2021
Figure 1 for Reward Shaping with Dynamic Trajectory Aggregation
Figure 2 for Reward Shaping with Dynamic Trajectory Aggregation
Figure 3 for Reward Shaping with Dynamic Trajectory Aggregation
Figure 4 for Reward Shaping with Dynamic Trajectory Aggregation
Viaarxiv icon