Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion
Proximal Policy Optimization (PPO) has become the de facto standard for training legged robots, thanks to its robustness and scalability in massively parallel simulation environments like IsaacLab. However, its on-policy nature makes it inherently sample-inefficient, preventing its use for continuous adaptation and fine-tuning on real hardware. Soft Actor-Critic (SAC), by contrast, is an off-policy algorithm that can reuse past experience, making it a natural candidate for sim-to-real transfer workflows where the same algorithm can be used both in simulation and for online learning on the real robot. Despite these advantages, SAC has consistently failed to match PPO's empirical performance in massively parallel training settings. This work identifies the root causes of this gap and introduces targeted modifications, covering policy initialization, timeout-aware critic targets, and multi-step return estimation, that enable SAC to train stably at scale. Evaluated across multiple legged robot platforms and diverse locomotion tasks, our approach closes the performance gap with PPO entirely.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL
Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games. However, their effectiveness is hindered wh…
Atari Gamescontinuous-controlContinuous ControlReinforcement Learning (RL)Bridging the Gap Between Value and Policy Based Reinforcement Learning
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Specifically…
Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Soft Options Critic
The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learnin…
Learning to Crawl: Latent Model-Based Reinforcement Learning for Soft Robotic Adaptive Locomotion
Soft robotic crawlers are mobile robots that utilize soft body deformability and compliance to achieve locomotion through surface contact. Designing control strategies for such systems is challenging due to model inaccur…
Reinforcement LearningSoft Actor-Critic-based Control Barrier Adaptation for Robust Autonomous Navigation in Unknown Environments
Motion planning failures during autonomous navigation often occur when safety constraints are either too conservative, leading to deadlocks, or too liberal, resulting in collisions. To improve robustness, a robot must dy…
Autonomous NavigationMotion Planning