Picture for Nasimul Noman

Nasimul Noman

Boosting Exploration in Actor-Critic Algorithms by Incentivizing Plausible Novel States

Add code
Oct 01, 2022
Figure 1 for Boosting Exploration in Actor-Critic Algorithms by Incentivizing Plausible Novel States
Figure 2 for Boosting Exploration in Actor-Critic Algorithms by Incentivizing Plausible Novel States
Figure 3 for Boosting Exploration in Actor-Critic Algorithms by Incentivizing Plausible Novel States
Figure 4 for Boosting Exploration in Actor-Critic Algorithms by Incentivizing Plausible Novel States
Viaarxiv icon

Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience

Add code
Sep 24, 2021
Figure 1 for Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience
Figure 2 for Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience
Figure 3 for Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience
Figure 4 for Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience
Viaarxiv icon

Optimal Actor-Critic Policy with Optimized Training Datasets

Add code
Aug 16, 2021
Figure 1 for Optimal Actor-Critic Policy with Optimized Training Datasets
Figure 2 for Optimal Actor-Critic Policy with Optimized Training Datasets
Figure 3 for Optimal Actor-Critic Policy with Optimized Training Datasets
Figure 4 for Optimal Actor-Critic Policy with Optimized Training Datasets
Viaarxiv icon