Deep-CFR
Deep-CFR copied to clipboard
Scalable Implementation of Deep CFR and Single Deep CFR
https://github.com/EricSteinberger/Deep-CFR/blob/master/DeepCFR/workers/la/sampling_algorithms/MultiOutcomeSampler.py as 'aprx_imm_reg' here is computed for every action and put to buffer without being summed up, I have no idea why 'aprx_imm_reg *= legal_action_mask / n_actions_to_smpl ' I think...
Currently game_env_cls is hardcoded in TrainingProfile class, which allows to run any limit-based game by passing to Driver an instance of TrainingProfile with a parameter like game_cls=Flop5Holdem. However, passing game_cls=DiscretizedNLHoldem...
Im getting this error on running the code: python paper_experiment_bigleduc_exploitability.py return _env.observation_space.shape[0] + self.action_vector_size TypeError: 'NoneType' object is not subscriptable did I missed sth on the running?