Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
Zhan, Guojian, Wang, Likun, Wang, Pengcheng, Zhang, Feihong, Duan, Jingliang, Tomizuka, Masayoshi, Li, Shengbo Eben
Maximum entropy has become a mainstream off-policy reinforcement learning (RL) framework for balancing exploitation and exploration. However, two bottlenecks still limit further performance improvement: (1) non-stationary Q-value estimation caused by jointly injecting entropy and updating its weighting parameter, i.e., temperature; and (2) short-sighted local entropy tuning that adjusts temperature only according to the current single-step entropy, without considering the effect of cumulative entropy over time. In this paper, we extends maximum entropy framework by proposing a trajectory entropy-constrained reinforcement learning (TECRL) framework to address these two challenges. Within this framework, we first separately learn two Q-functions, one associated with reward and the other with entropy, ensuring clean and stable value targets unaffected by temperature updates. Then, the dedicated entropy Q-function, explicitly quantifying the expected cumulative entropy, enables us to enforce a trajectory entropy constraint and consequently control the policy long-term stochasticity. Building on this TECRL framework, we develop a practical off-policy algorithm, DSAC-E, by extending the state-of-the-art distributional soft actor-critic with three refinements (DSAC-T). Empirical results on the OpenAI Gym benchmark demonstrate that our DSAC-E can achieve higher returns and better stability.
Nov-18-2025
- Country:
- Asia
- China > Beijing
- Beijing (0.04)
- Middle East > Jordan (0.04)
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- Singapore (0.04)
- China > Beijing
- Europe
- North America
- Puerto Rico > San Juan
- San Juan (0.04)
- United States > California
- Los Angeles County > Long Beach (0.04)
- Puerto Rico > San Juan
- Asia
- Genre:
- Research Report (0.64)
- Technology: