Policy Gradient Methods
Twin Delayed Deep Deterministic
Introduced by Fujimoto et al. in Addressing Function Approximation Error in Actor-Critic MethodsTD3 builds on the DDPG algorithm for reinforcement learning, with a couple of modifications aimed at tackling overestimation bias with the value function. In particular, it utilises clipped double Q-learning, delayed update of target and policy networks, and target policy smoothing (which is similar to a SARSA based update; a safer update, as they provide higher value to actions resistant to perturbations).
Source: Addressing Function Approximation Error in Actor-Critic Methods
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Reinforcement Learning (RL) | 64 | 23.36% |
| Deep Reinforcement Learning | 53 | 19.34% |
| Reinforcement Learning | 47 | 17.15% |
| Continuous Control | 29 | 10.58% |
| OpenAI Gym | 9 | 3.28% |
| Decision Making | 8 | 2.92% |
| Autonomous Driving | 6 | 2.19% |
| Offline RL | 5 | 1.82% |
| Meta-Learning | 4 | 1.46% |
Adam
Clipped Double Q-learning
Dense Connections
Experience Replay
ReLU
Target Policy Smoothing
