REVIEW 5 cited by
Discrete and Continuous Action Representation for Practical RL in Video Games
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Discrete and Continuous Action Representation for Practical RL in Video Games
read the original abstract
While most current research in Reinforcement Learning (RL) focuses on improving the performance of the algorithms in controlled environments, the use of RL under constraints like those met in the video game industry is rarely studied. Operating under such constraints, we propose Hybrid SAC, an extension of the Soft Actor-Critic algorithm able to handle discrete, continuous and parameterized actions in a principled way. We show that Hybrid SAC can successfully solve a highspeed driving task in one of our games, and is competitive with the state-of-the-art on parameterized actions benchmark tasks. We also explore the impact of using normalizing flows to enrich the expressiveness of the policy at minimal computational cost, and identify a potential undesired effect of SAC when used with normalizing flows, that may be addressed by optimizing a different objective.
Forward citations
Cited by 5 Pith papers
-
Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation
Dmsh is a new multi-agent RL framework that formulates mesh generation as an MDP and uses three coordinated agents plus curriculum learning to produce globally conforming all-quad meshes without post-processing.
-
Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding
Hybrid RL-MPC trained on the full hybrid action space parametrizes continuous MPC via discrete rollouts and a critic terminal cost, yielding near-MINLP F1 strategies with recursive feasibility under a structural assumption.
-
Revisiting Action Factorization for Complex Action Spaces
Comparative study of action factorization methods for hybrid action spaces across PPO/SAC/DQN finds branching dueling architectures effective and auto-regressive methods highest performing, with new VDN-PPO and PPO-MI...
-
Hybrid TD3: Overestimation Bias Analysis and Stable Policy Optimization for Hybrid Action Space
A weighted clipped Q-learning target that averages over discrete action choices makes TD3-style training stable for hybrid-action robot manipulation.
-
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
RAID finds multiple diverse game exploits by sequentially training RL agents and masking previously discovered strategies from the reward function.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.