2 results found Sort:

MarcoMeter
episodic-transformer-memory-ppo MarcoMeter
18
149
mit
4
Clean baseline implementation of PPO using an episodic TransformerXL memory
ppo trxl gtrxl pomdp pytorch on-policy memory-gym transformer actor-critic transformer-xl episodic-memory policy-gradient gated-transformer-xl deep-reinforcement-learning proximal-policy-optimization
Created 2022-05-04
9 commits to main branch, last one 4 months ago
MarcoMeter
recurrent-ppo-truncated-bptt MarcoMeter
16
122
mit
4
Baseline implementation of recurrent PPO using truncated BPTT
gru ppo bptt lstm pomdp pytorch on-policy recurrent truncated recurrence actor-critic deep-learning policy-gradient recurrent-neural-networks deep-reinforcement-learning proximal-policy-optimization
Created 2021-06-07
13 commits to main branch, last one about a year ago