mixing-on-and-off-policy-data

There are 1 repository under mixing-on-and-off-policy-data topic.

parralplex / elite_buffer_vtrace
Distributed RL platform with modified IMPALA architecture. Implements CLEAR, LASER V-trace modifications along with Attentive and Elite sampling experience replay methods.
machine-learning impala experience-replay deep-reinforcement-learning pytorch distributed-reinforcement-learning elite-sampling arcade-learning-environment actor-critic-with-experience-replay policy-gradient mixing-on-and-off-policy-data
Language:Python 6