Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives
While Soft Actor-Critic (SAC) is highly effective in continuous control, its discrete counterpart (DSAC) performs poorly on challenging discrete-action domains such as Atari. Consequently, starting from DSAC, we revisit the design of actor-critic methods in this setting. First, we determine that the coupling between the actor and critic entropy is the primary reason behind the poor performance of DSAC. We demonstrate that by merely decoupling these components, DSAC's performance significantly improves. Motivated by this insight, we introduce a flexible off-policy actor-critic framework that subsumes DSAC as a special case and yields novel objectives. Our framework allows using an m-step Bellman operator for the critic update, and instantiates the actor objective by combining standard policy optimization methods with entropy regularization. Theoretically, we prove that the proposed methods can guarantee convergence to the optimal regularized value function in the tabular setting, generalizing the results in prior work. Empirically, we evaluate the proposed objectives on standard Atari games. Our ablations indicate that, unlike DSAC, these objectives, including novel ones, perform robustly even without entropy regularization or explicit exploration mechanisms.
Code (0)
등록된 구현이 없습니다.
Tasks
Continuous ControlAtari GamesSimilar Papers 제목 키워드 기반
Soft Actor-Critic for Discrete Action Settings
Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings. Many important settings involve discrete actions, however, and s…
Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)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)Revisiting Discrete Soft Actor-Critic
We study the adaption of Soft Actor-Critic (SAC), which is considered as a state-of-the-art reinforcement learning (RL) algorithm, from continuous action space to discrete action space. We revisit vanilla discrete SAC an…
Atari GamesQ-LearningReinforcement Learning (RL)On Problems of Implicit Context Compression for Software Engineering Agents
LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than…
From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval
Discrete tokenizers have emerged as indispensable components in modern machine learning systems, particularly within the context of autoregressive modeling and large language models (LLMs). These tokenizers serve as the …
Information Retrievalmultimodal generationRecommendation SystemsSurvey